diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e70ca59c85789e08d18b8c85d854c985d730b8f6 --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 140, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.53.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model-00001-of-00050.safetensors b/model-00001-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88ff9a770961f539d5a86c546a256a85bd67489f --- /dev/null +++ b/model-00001-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfd4a6dffa9e08dbf09169b520e1293f995cea5d03edd922183c81dee798d05 +size 4672471504 diff --git a/model-00002-of-00050.safetensors b/model-00002-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6065572e3164bc5268fd04ee9f28776e9795b528 --- /dev/null +++ b/model-00002-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd57bb8e82f9abac32c14b4afee109d1c6cddcf0bc28fafb5e9f1a50f5ec93f3 +size 4831922704 diff --git a/model-00003-of-00050.safetensors b/model-00003-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00194e11165aa32dc291443629aa65048166070b --- /dev/null +++ b/model-00003-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420251f69dad1a024f8c077e587cd253887a8ae41a9c62b7c5030ae1c558dc5c +size 4966190768 diff --git a/model-00004-of-00050.safetensors b/model-00004-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e07472fa63ac4c2e0e0a89567430660c09b0e4c --- /dev/null +++ b/model-00004-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd7454fd82b9ee9b99abe7edaabb2d4e27adb68ad6169a2604f9fb20953c791 +size 4831906224 diff --git a/model-00005-of-00050.safetensors b/model-00005-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e82a29d36fbec8bb243353d705fb07e435bca7cb --- /dev/null +++ b/model-00005-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31d785c244c726f6f89b604186905e00716efabd661a5bca0e54fcaeea49a53 +size 4999711736 diff --git a/model-00006-of-00050.safetensors b/model-00006-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7036cde3c8b0139e42592477a24dc321fc8f8647 --- /dev/null +++ b/model-00006-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f8094e3eaa1cb22853c2917b87e7d7b89b264f610a133bd28a19de4e856ed8 +size 4798385256 diff --git a/model-00007-of-00050.safetensors b/model-00007-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..522536a9d01b9f4b998f4fb8dc87e5eb7e7fe1eb --- /dev/null +++ b/model-00007-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61aa5fac8d4fa915a5fd92deb107cfc97bb4ae71c26987b2ade91b6a08b23f67 +size 4831906216 diff --git a/model-00008-of-00050.safetensors b/model-00008-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5a42ce4a74b1a0e2433640054dde858e0f52cde --- /dev/null +++ b/model-00008-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232e7f3a335d1d37d9100a0d51b900e03ef02ff03775151d73e9b972a03870cb +size 4966190760 diff --git a/model-00009-of-00050.safetensors b/model-00009-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afcc2777488a46824dfcc75a3d31134fc413876d --- /dev/null +++ b/model-00009-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147bb6fc040e688477fac58c15708f653d1363ea9f9ae76df471097907df9369 +size 4664167408 diff --git a/model-00010-of-00050.safetensors b/model-00010-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82d9eb215ceda761bbbb6f24c555b38147c1158e --- /dev/null +++ b/model-00010-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948411ff0dd6899ca30ac55aacbea8b75e8b46d3352370b23f7b8f89bee21c41 +size 4831906224 diff --git a/model-00011-of-00050.safetensors b/model-00011-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af2d1db6324147b04db429f138999c75931604dd --- /dev/null +++ b/model-00011-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b797b2b8e03177445e65a316bd0139494178d9ddd5d155624c8892b163be55d5 +size 4999711736 diff --git a/model-00012-of-00050.safetensors b/model-00012-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c7601e99e6bc6deaf6e72a6bf9bc786826cb278 --- /dev/null +++ b/model-00012-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dfa2052867a31b909847e56544823cf446a2f059011f8783dbca209bef1c03c +size 4798385256 diff --git a/model-00013-of-00050.safetensors b/model-00013-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34a3098c41b1b8bf25e53452d0a812e351662e42 --- /dev/null +++ b/model-00013-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c6d997d68dd8f73f87479799c91b4a3738bc13721ec26ca6aa5470a7de7c30 +size 4831906216 diff --git a/model-00014-of-00050.safetensors b/model-00014-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77b3da74b13d982852ce227f0f54ec25bd7f7182 --- /dev/null +++ b/model-00014-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aadd97a89c15b18fb0b0c33870a3e44e5346a339f8f534d00311eef250998d1a +size 4966190760 diff --git a/model-00015-of-00050.safetensors b/model-00015-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ccb4c60a8a13e00334df575beace59ed2125e23 --- /dev/null +++ b/model-00015-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e21fa1dfbf882ecba62fc60dffa3e988b553ec8143bb75673326ba626b73cc4 +size 4831906224 diff --git a/model-00016-of-00050.safetensors b/model-00016-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4249958b6db843a89c8c066106c8b3268ac2f88 --- /dev/null +++ b/model-00016-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d4560d247f7c1efcff7669ac0dc94080748d09222ac8ab9e9b7deceb559595 +size 4966174264 diff --git a/model-00017-of-00050.safetensors b/model-00017-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca4bd25139dda983883242463e1ccaed390f5963 --- /dev/null +++ b/model-00017-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36dd592ea3f81b02e3e50b9a293fc564037a8d1c69739c79219706edaad55abe +size 4966140568 diff --git a/model-00018-of-00050.safetensors b/model-00018-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..14bdf0bcdef412f9264cce5d970b5a1a3db83214 --- /dev/null +++ b/model-00018-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c66e593d05ceeca20cf49792543528fce1ede7d0109c9c1bfbf5445af3888510 +size 4999711720 diff --git a/model-00019-of-00050.safetensors b/model-00019-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2e1ee810ca40cd787ffd646df7ba16e92d65234 --- /dev/null +++ b/model-00019-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ff27a81ebc990a102542facc9ed73d298c45ecf797cc7f15e085c732fd0219 +size 4999711736 diff --git a/model-00020-of-00050.safetensors b/model-00020-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83aff2984dbdb84d0a3801d9ab2cf8f634648da1 --- /dev/null +++ b/model-00020-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9447f61a65483aefd6ee7e21b011d6b73cf26988b54c834c9ba52185adeb422b +size 4798385256 diff --git a/model-00021-of-00050.safetensors b/model-00021-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f1ed8800f521d64fcfd7d64d07da3fc5abec4f3 --- /dev/null +++ b/model-00021-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc57cee5b6dc6c0d4d00b09af189a813eaa9ed1dc6c06f461491e5b11f59e09 +size 4831906216 diff --git a/model-00022-of-00050.safetensors b/model-00022-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d899fd0bef18e097b888b5afc1b17c4133c59b8 --- /dev/null +++ b/model-00022-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4a95f28346ad597f05603e04ce853ea82e57e1a60636bd62265d843a9d2e43 +size 4966190760 diff --git a/model-00023-of-00050.safetensors b/model-00023-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8b606efb1ddea92536a34aa29879fc48bfc9a77 --- /dev/null +++ b/model-00023-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0696af276300c3593a3e2daaf3e51c401a001adbcd6b12c38bdc1e2b4f60db11 +size 4831906224 diff --git a/model-00024-of-00050.safetensors b/model-00024-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f08b87d0419f1a8dc219112695b9de2b4554d44 --- /dev/null +++ b/model-00024-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50c4ea27303c3dfe0bfdfd1c56ca857169a330d00b9ce403fec467c96b631b3 +size 4664167400 diff --git a/model-00025-of-00050.safetensors b/model-00025-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2adbadd63fd79c233bb96e6cc24f10dbaca4503e --- /dev/null +++ b/model-00025-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbb4e74290cbde40ff2c032f1940508a95b81382a984cd00f9813474e03a95e +size 4999711736 diff --git a/model-00026-of-00050.safetensors b/model-00026-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..deed37898bca6984764266b8f5c99ffff5ca2ede --- /dev/null +++ b/model-00026-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c89a1199b9ece047d821aa62c3577e0211f7916890b4bfbd799d43acbf7b1e +size 4798385256 diff --git a/model-00027-of-00050.safetensors b/model-00027-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3cf8df04ea6c44cf6f14c7e6d404c860b4decb8 --- /dev/null +++ b/model-00027-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d904c421f44777a12b8460e5b7e35f141b27ff2ce9de06eece2e3b61c9ed6d +size 4831906216 diff --git a/model-00028-of-00050.safetensors b/model-00028-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17001059bba6f7309ccc56fbe0d5b6ff7fb2f500 --- /dev/null +++ b/model-00028-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a86fe9e16024aea2880ca2630209e7ae1c148f2d45a130261fded3358152c7e +size 4966190760 diff --git a/model-00029-of-00050.safetensors b/model-00029-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..117185dc8acdf18a409d3c72e87f695972d2ec0b --- /dev/null +++ b/model-00029-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9205d8cc1cd96aca882ecfb36a6379f87a0d39290af8c03bdc7f3580bd60e970 +size 4831906224 diff --git a/model-00030-of-00050.safetensors b/model-00030-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a001300f28b2021d9d9166b3eaef6770f01b5b71 --- /dev/null +++ b/model-00030-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f64bcc484fe84b550e2b403a3d0c1f9c32824da3c9d5fd9cfe85e4bbe788dcc +size 4966190768 diff --git a/model-00031-of-00050.safetensors b/model-00031-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e69ac51626c02c53c265f873627043a0268d751f --- /dev/null +++ b/model-00031-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91594d43f295a8e0e3c6c548fbd193d82875a1edb2d10a0af575334647415b7 +size 4982901392 diff --git a/model-00032-of-00050.safetensors b/model-00032-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5feadf99fbf4d0491902d6d989057f1b67e8bb8 --- /dev/null +++ b/model-00032-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b592661a2cc40657d0116f7dccb6030625ce93bdaf42cb39e62c859dabe84c +size 4982934392 diff --git a/model-00033-of-00050.safetensors b/model-00033-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..070c43a7b78dc1cf8caa6be595e670680c55de53 --- /dev/null +++ b/model-00033-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e7aeced84f7439328d26d58d8e4f98ae258880b5f655d28ff08044c9cc7b3c +size 4999711752 diff --git a/model-00034-of-00050.safetensors b/model-00034-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f744baab87ca7fe407e2c9d21e353ed5def7c62 --- /dev/null +++ b/model-00034-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67641a1740bb50b522cd9a33667934651ecd6fb143e3a164189eb22a717f9255 +size 4798385264 diff --git a/model-00035-of-00050.safetensors b/model-00035-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4306e1cb094db080769087d0c532a2c8aacd0563 --- /dev/null +++ b/model-00035-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e05aa97e36c5fa52b1ecf81da15d454360bcfd7dc7d4e37ac81a1740ddf9a1 +size 4831906232 diff --git a/model-00036-of-00050.safetensors b/model-00036-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4f3356b0121b0cd2438605ea5afc41f21b1bc94 --- /dev/null +++ b/model-00036-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcd5811536b5c12b601f1f91a0016bd49aa64eebf2f32f5cca97200497e59cf +size 4966190784 diff --git a/model-00037-of-00050.safetensors b/model-00037-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4b350dcfc4014e9593d1026081139fa23632bf1 --- /dev/null +++ b/model-00037-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9033fa3db74aa48dc47966a03d95e376d652caaa21095f30966183d182be7207 +size 4831906232 diff --git a/model-00038-of-00050.safetensors b/model-00038-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1b1d42d88a8cd98f7f69070b7bbf268990b9912 --- /dev/null +++ b/model-00038-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bdf97d628f72f83c7a508c43873e2fb7bb51687c74e6f576260f8597317ca9 +size 4966174288 diff --git a/model-00039-of-00050.safetensors b/model-00039-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc809b2f3bb9828594c56e34420a3a966331a4cb --- /dev/null +++ b/model-00039-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2f99dea7c8b82f423bc4a98829ba904073badf82de0b103b3f92a044080628 +size 4966140568 diff --git a/model-00040-of-00050.safetensors b/model-00040-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..249954edc645c1d663d17903d1f462abefca303b --- /dev/null +++ b/model-00040-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3407cc8a7c45a1562bd8101b7c67049a84a0f80b868c3fb962ea251508806227 +size 4999711752 diff --git a/model-00041-of-00050.safetensors b/model-00041-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..796a7c44d13c905bd8fae4cafabe7a428b274238 --- /dev/null +++ b/model-00041-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe13798829adc9384249a200f5295eab05d2ece3dbbe46975ddfdb6ccda16953 +size 4999711760 diff --git a/model-00042-of-00050.safetensors b/model-00042-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5a1c4b9e0583e94c68268236a809aee5f3d40be --- /dev/null +++ b/model-00042-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456f1a933e9ae8b5f2bfc92f97498ddccb9c4a9f552eacc90a239f7078847a17 +size 4798385280 diff --git a/model-00043-of-00050.safetensors b/model-00043-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ab23713ad9e03dd86e768f772427a79ddbdb4e7 --- /dev/null +++ b/model-00043-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84240ddd258a2b171ef2d4487aaead409cc5b6d20f42bddb8dfa8079ffca060 +size 4831906240 diff --git a/model-00044-of-00050.safetensors b/model-00044-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0d14566da6ce4a5c6673a697ae7d97fd72f067a --- /dev/null +++ b/model-00044-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1fd844aee08d3384fb487e6d7542f5ac54e263ec56a1fe738a54110b2d5cbe +size 4966190792 diff --git a/model-00045-of-00050.safetensors b/model-00045-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5107609f54edc4b682c4ca09f5d8b20759beb519 --- /dev/null +++ b/model-00045-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47c209c8c01bad1ebf66e785f8698a2a3401963277cbefdbb16ffcd14fbdbb2e +size 4831906240 diff --git a/model-00046-of-00050.safetensors b/model-00046-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb1458874abf8654863c84630dc708106ab9cb71 --- /dev/null +++ b/model-00046-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae8967da3a49dc30a78c2a535c3ad91247791478620756d9985978dbc62bc95 +size 4966174288 diff --git a/model-00047-of-00050.safetensors b/model-00047-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9559c91f274f715a180392574220e5b693dd32cc --- /dev/null +++ b/model-00047-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3045d33350c3fb79e940c4dcd929ca62c32daf2e0805fdafa6b1206361e9ed +size 4982917928 diff --git a/model-00048-of-00050.safetensors b/model-00048-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c770bee4c267c2a42d5f3fd951581bd5c98fce2 --- /dev/null +++ b/model-00048-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da924cc458c8f7cf749bbd4132d2697f489a7335fa747c6cfa7a8acd6b4a02c +size 4999711760 diff --git a/model-00049-of-00050.safetensors b/model-00049-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4df83ab8ec3f5998eefb46bed97ba85db9c80396 --- /dev/null +++ b/model-00049-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ac1ed15f29e5b80c38ff1dec161fd2e57959842f96715c0b3df143e690fc0d +size 4647373600 diff --git a/model-00050-of-00050.safetensors b/model-00050-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..755b1bac5f912a923659efb4a231323730322387 --- /dev/null +++ b/model-00050-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a55f3c1a19b37ff2a6ad580696153ee889ce0c6d5a3e9abb362d5db0191f0b8 +size 4194405216 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..89ea6a8826e069a2e36885134c278f7f2ecf2798 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00050.safetensors", "model.embed_tokens.weight": "model-00001-of-00050.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.44.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.45.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.47.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.58.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.68.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.80.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.83.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.84.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.86.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.87.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.79.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.89.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.input_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.101.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.94.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.104.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.105.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.97.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.107.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.108.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.6.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.122.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.125.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.126.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.126.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.118.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.128.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.128.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.128.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.129.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.129.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.131.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.131.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.133.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.norm.weight": "model-00050-of-00050.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..41cd8d1ca52c3fc5feaf8445ca922b27f8e8ea8b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}