Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BioMistral/BioMistral-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,11 @@
+base_model: BioMistral/BioMistral-7B
+gate_mode: approach # one of "hidden", "cheap_embed", or "random"
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts:
+  - source_model: Treza12/BioMistral-7B5
+    positive_prompts:
+      - "This is a prompt that is demonstrative of what expert_model_1 excels at Diagnosis"
+  - source_model: cognitivecomputations/WestLake-7B-v2-laser
+    positive_prompts:
+      - "Answer this question from the Winogrande test."
+      - "Use advanced knowledge of culture and humanity"

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8008a285475a5907277eadb6e7c4ca07004cda37ecfe0adbb7f3a5086019bde5
+size 933250496

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9b2563a41b58f2262dcbb00bf9143a36cfa8784627938c703f75fe0a726424
+size 989890824

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd1263dfa51d29e10ce77c89d2c97ae38927155871e8e80972a4b0c9e2424be
+size 905987672

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fe830d8928d171146d2693ca72046b8ce44ef9e7fc872b51a13d5e20d5caa4
+size 905987672

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d0b848fe44df88f06bac64ab04bce0433f8cbac0357c9aea813a8fd3920ff3
+size 905987672

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69898e9df69af11705b57e858b00c4f16dc5f8386b87bcf9829ebd0ac54e979
+size 905987672

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de13e0cf1abd07ef4df6559834ef4149ef4810e852a692cf314a9607287bb24d
+size 905987672

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bbc8047687b593b20b76d0e7db42d70772868e9e90c920ce21d27af970c608
+size 989890824

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a67621839ee1718ab61a67c0be1c7465b2486c72a3da2a793afdf5d6f02995
+size 905987680

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bac223f85fad2c3c49cae091770dba1fee5deecdc7e49c470beffac181ce53e
+size 905987688

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3226fa94ebdd33a1344483982ed6e4158bf7ab4376211a64056c18120bc65619
+size 905987688

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aba1fb93589b2942da1179175ce9d6e0df2268c368cb6c3abe99130816e3731
+size 905987688

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd703d5e710e5b3a0318acd398517cced0aedba89d1ba82b72ff4bb9838da8df
+size 905987688

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e728ea2c00efbdb87116c2c43da0fca2900ee22f2a94a89f68d38d9697ea4a2
+size 989890840

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0aaab19198732051e8bd318cdcee429b382c62cf2a9a0c1928b284ccc4586b5
+size 905987688

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c606cf64cf46bb11ec1ba062b45d0adb67f0b7ca8b0b58d55ef247af18084b63
+size 905987688

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73bc703a07ece3f3bc1d656e616dd96404801575cb953544163be4cae36bc23f
+size 905987688

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2c05de1beec54fc97dc5a194bbd42807e5690fbd801850dd6181934a5a71c6
+size 905987688

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563fd88875a57b38af657495596d00b3ca77e44f10065c3343d0f21a1cf2bf0b
+size 905987688

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1f158cf152a80161329143baa2f921d1ef5f02f3c7e10bd90c45be57537872
+size 989890840

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233d25079cd67699a9aa9ce4257d2cf80a96742e2e40c2e5a73d0f2d73e8fe28
+size 905987688

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdb284b13d83cf043c05ec51136603e53d3e0446963187ce0f030234552dfc8
+size 905987688

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3119cc257c784bbb85eec78f8c4d7e65ba0418f07fd4b688155a48bdf8a3c2e5
+size 905987688

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd09a23365c0bfe515aba4c4611f050ceaaeb4bc70522fa3f37b7b064ac84bd9
+size 905987688

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c0b9ee4c7f7e348633f1d3691ff795f08f1197c30b1e5225e3bbee6440fba7
+size 905987688

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674981a0516e0f554990a72aaacdc107c0b0b715351a6cff26ff718b2e0a74b6
+size 989890840

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4c140a8eb152e67d1052fe8409c696dba684d0dc5a9e5b376bc7a03ae8733b
+size 905987688

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe8c621911cb2daa52c8a00b88aa901769553c68256112feed90173dd1d642b
+size 849883672

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 25758277632}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors", "lm_head.weight": "model-00028-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}