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/.ipynb_checkpoints/config-checkpoint.json b/.ipynb_checkpoints/config-checkpoint.json new file mode 100644 index 0000000000000000000000000000000000000000..ea053f1cbc06b963532eb2dd3c7594902832b582 --- /dev/null +++ b/.ipynb_checkpoints/config-checkpoint.json @@ -0,0 +1,42 @@ +{ + "_name_or_path": "unsloth/Llama-3.3-70B-Instruct", + "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": 120, + "num_key_value_heads": 8, + "pad_token_id": 128004, + "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": "4.48.0", + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..ea053f1cbc06b963532eb2dd3c7594902832b582 --- /dev/null +++ b/config.json @@ -0,0 +1,42 @@ +{ + "_name_or_path": "unsloth/Llama-3.3-70B-Instruct", + "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": 120, + "num_key_value_heads": 8, + "pad_token_id": 128004, + "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": "4.48.0", + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} diff --git a/model-00001-of-00044.safetensors b/model-00001-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62566103bf5960dd07e8c445506e3a6a8b3c94cf --- /dev/null +++ b/model-00001-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5a0177f660b3f18caddb2f70db303369c3503ef6d6e7dc9c3c0a23bd7eb4f4 +size 4672471504 diff --git a/model-00002-of-00044.safetensors b/model-00002-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..be0a173447f4ea4f291d7254537877eba3df430a --- /dev/null +++ b/model-00002-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:201d329eed0f51dd199d3d3a499da099a2578e8a0287bd62cc641bc973c50360 +size 4664167400 diff --git a/model-00003-of-00044.safetensors b/model-00003-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e4c09aa7269477c070aa1eef5f46a8257f7d5e5 --- /dev/null +++ b/model-00003-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ba5a76bae995d29f92d958a87f50043b66b40c1e9eb531742d795bebc97e7c +size 4982917904 diff --git a/model-00004-of-00044.safetensors b/model-00004-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..470e66774bdd79a6d3deeab0b166d741c1244975 --- /dev/null +++ b/model-00004-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944ecfc749edee88f6832c975a3f7365bde10f2275a3cbfa8ba155e35f835dfb +size 4999711736 diff --git a/model-00005-of-00044.safetensors b/model-00005-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..075f99da164c93a432f5482f735ac5e9fae79558 --- /dev/null +++ b/model-00005-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c21b0c162d0fc5ecd810149eb4029f39f13100e4322e2e7801e522bc271a51a +size 4647373576 diff --git a/model-00006-of-00044.safetensors b/model-00006-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4a9a9b2770c70904cba7c52097d82201146f568 --- /dev/null +++ b/model-00006-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faaca74ca4d0ee932ff4709a81ae73fc0bd049f2f708c0732cea0742022ef6f5 +size 4664167400 diff --git a/model-00007-of-00044.safetensors b/model-00007-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64c0dad9537e3510f77f118e7f44666525cbcac8 --- /dev/null +++ b/model-00007-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62253d3b26f323666fbb1c831cff59b11623df3fcc03137c62d2689d3d4650ad +size 4664167416 diff --git a/model-00008-of-00044.safetensors b/model-00008-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51950984a98550219182a214dcee331d1005de08 --- /dev/null +++ b/model-00008-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4796292283b861549730c2f07ebf7f0b97657d98c6c5b00a0d4ecebb7603c3 +size 4982917904 diff --git a/model-00009-of-00044.safetensors b/model-00009-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdd99f20121f9a49ae5fa9ad0a2016bb08445c6c --- /dev/null +++ b/model-00009-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6ae1cbe03b947ac70e2c5897bfaa809dc4d594c97b298817f38a79d8d2b99f +size 4999711736 diff --git a/model-00010-of-00044.safetensors b/model-00010-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e458bbdc13b38f8715539b16fb1294d2b9f2d5b1 --- /dev/null +++ b/model-00010-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8759561a83d9ab1884620cc2aa40e4e82361f7302e2feee4a0a704731705a2b1 +size 4647373568 diff --git a/model-00011-of-00044.safetensors b/model-00011-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de00455fc63f194eb4372250eb4abc1c15aa8b92 --- /dev/null +++ b/model-00011-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b93eaefae98edb9f66cc5992ed95195a2c4f5f739ac3cedb5c740c930be7491 +size 4664167408 diff --git a/model-00012-of-00044.safetensors b/model-00012-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9512d2c3553af2fd433f76f608fe2b13fdd1602 --- /dev/null +++ b/model-00012-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d90ac61804de65f6b0aedd754b1f5846a07e751437b171663c854416b06c306 +size 4664167416 diff --git a/model-00013-of-00044.safetensors b/model-00013-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7593086716b07c32fc04d6d2bbd8f7baee7e0bb4 --- /dev/null +++ b/model-00013-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8a17b375a8b1f109aa3a0d62480ded8f4e5309037c7532a8d817cbff0cef98 +size 4982917904 diff --git a/model-00014-of-00044.safetensors b/model-00014-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c23e747115a61858b89956fad8f4a368cc688907 --- /dev/null +++ b/model-00014-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154a415e53987639519e78a786adc6093eba5cd7637e48d4a34b7c66e111e2b8 +size 4999711728 diff --git a/model-00015-of-00044.safetensors b/model-00015-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95b977809f13e264aca06ffc9d5a96eded616c4b --- /dev/null +++ b/model-00015-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54d8d69d286e4bccf006e03fb098f6ded2d36d116b6148ea699f7b3c70b47b4 +size 4647373576 diff --git a/model-00016-of-00044.safetensors b/model-00016-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a9f38e7115f85d52a9ec4b112053ea4fd5acbeb --- /dev/null +++ b/model-00016-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6022ca098f53488bd1e05acd8a779fbde8d69e91a5c3c249cba59c9dbc4400e2 +size 4999727520 diff --git a/model-00017-of-00044.safetensors b/model-00017-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d00da7fdb64b54011065ca24cb48faa604e46fd --- /dev/null +++ b/model-00017-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6b5f320d46b0d83254cd9cb6aa8caf39da813e518cd78bf7f8c8680723e68a +size 4664117880 diff --git a/model-00018-of-00044.safetensors b/model-00018-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f68dc3d6e88bf2090a40d28e656616e4a362ef9 --- /dev/null +++ b/model-00018-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de0ab3e0e6cff2f7c208b3e5d77faf6d10e9abb54e40b78a103d9e5a44a4676 +size 4664167408 diff --git a/model-00019-of-00044.safetensors b/model-00019-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4247b27eb1f00006ea8197a5a7c8b15d3c765b6f --- /dev/null +++ b/model-00019-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a99ccd36935d696903af38eef522b06c3dd214b251c86f4808c7c62fb0d38d +size 4664167416 diff --git a/model-00020-of-00044.safetensors b/model-00020-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c333085f34b3451f92251a4a919c9ab9a1475d54 --- /dev/null +++ b/model-00020-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f46f6c3abf19b622b8565a324980fbfecbff7b9b0171b52a5177d499e3a87d8 +size 4664167408 diff --git a/model-00021-of-00044.safetensors b/model-00021-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c2761caf570d4cb4c83d78e8af1cf08fee424dd --- /dev/null +++ b/model-00021-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27eb181922f1cd174192c88fe439dc129e0014843111cdc35aa4827513fb699c +size 4966190760 diff --git a/model-00022-of-00044.safetensors b/model-00022-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe56c2478dd32340a566d534191f830a73d8b844 --- /dev/null +++ b/model-00022-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:941662a14b550cde75d128447395f761d1b038dac079a09e0ec9450acfc3ebb5 +size 4664167416 diff --git a/model-00023-of-00044.safetensors b/model-00023-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7492832edc697c6aaf3f5b805f0ac7bd3844f94 --- /dev/null +++ b/model-00023-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4b65557a416df6156e637ff4cd72ead14840330df9b881f026c0b9c307707b +size 4949330248 diff --git a/model-00024-of-00044.safetensors b/model-00024-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2aed29a7860be14b6646f0f357d2ecdde1eb6748 --- /dev/null +++ b/model-00024-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888e959d3e61e8af6176efa197ef772d318637477858a146c768f28016982d68 +size 4999711728 diff --git a/model-00025-of-00044.safetensors b/model-00025-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a020012f6645517bda58055a101e7a8dcafd5883 --- /dev/null +++ b/model-00025-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0310483cdbf1c67c0597d28d7f68de337c660e3536e6d33d50aa31f5ab559bc6 +size 4999711728 diff --git a/model-00026-of-00044.safetensors b/model-00026-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f99bb6491687087840b0250d0279bf14eedee0c5 --- /dev/null +++ b/model-00026-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0149cc420d71d26476d7089a2f6d272277c2424c72cf04e50a317e7e6069b9c +size 4999711728 diff --git a/model-00027-of-00044.safetensors b/model-00027-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7545b526442d259ae88175934080fb8d8f332734 --- /dev/null +++ b/model-00027-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a32541ec5ea26ee748ecc0f35975995dc0dbb018b08d0263a31114c82af8e8c +size 4999711728 diff --git a/model-00028-of-00044.safetensors b/model-00028-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dfb8d038fcf87dcbbd8a4293e5113750e34e069e --- /dev/null +++ b/model-00028-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f65eccb6f0bc499df6044a9c014bf68694f0ceb7e46e1851d2eee6c5d9138a3c +size 4999711720 diff --git a/model-00029-of-00044.safetensors b/model-00029-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d34cd76f0c4b6a973c4d063dc718525f32a3a8e4 --- /dev/null +++ b/model-00029-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08f14595b736cca13623685fe49e03d0d03e31405d3d48366918d6caccdc346 +size 4613785888 diff --git a/model-00030-of-00044.safetensors b/model-00030-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a354762830c6cc8bd7e9571b16fc05662180e63c --- /dev/null +++ b/model-00030-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3db841a4127dd0122ea653fba36be6ad6de778482013663593a2057661f5e54 +size 4664167408 diff --git a/model-00031-of-00044.safetensors b/model-00031-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d71f3f81e9d0ab4630c5296bae25bab648aa3441 --- /dev/null +++ b/model-00031-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92966262634eae5f510565698bdd2d44ffede7bfc8a2a861b3f0e42f747fdcf +size 4664167416 diff --git a/model-00032-of-00044.safetensors b/model-00032-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11d685e970f22e061ce91ec2f0c27479b6933dfd --- /dev/null +++ b/model-00032-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4cbc394f62994e047aa381c0b6029ed0e0f63491bc4bb49b1bb653ad78a79c4 +size 4966190760 diff --git a/model-00033-of-00044.safetensors b/model-00033-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b950f5ae0a1c5b8ca511905f3cd17ae0e619a08 --- /dev/null +++ b/model-00033-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d42c1d97a61a877d0aba13a60acbe2839b71eea08a6104ad635181faa71fe4 +size 4664167416 diff --git a/model-00034-of-00044.safetensors b/model-00034-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8dea5da72d0c4898b5115827dd6f0bb26c14c2de --- /dev/null +++ b/model-00034-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7ac0b0e238f7bbac7e60550fc78a5c013e7b087bc1798348fcfcba40383a0a +size 4664167416 diff --git a/model-00035-of-00044.safetensors b/model-00035-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a33361d3abb386c6ff20e3691649d1ec4d55cca --- /dev/null +++ b/model-00035-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f75d48b12b224f934f2772bd6a7a8be8200b313e87ee6f750e27af287ef8ba1 +size 4949330248 diff --git a/model-00036-of-00044.safetensors b/model-00036-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f335ebafa79cd7c99e9056d0f9c29b36a3c4c0f --- /dev/null +++ b/model-00036-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efaeb6208c65050505b278f3470ee3f6e0e7bd71adfd2604717a72039d5ec49a +size 4999711744 diff --git a/model-00037-of-00044.safetensors b/model-00037-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5734c9d5965b4c954354553bc1308cdd6ddfe345 --- /dev/null +++ b/model-00037-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4a38dbd16f06dc0c98db18816ffbf443eb8fde3671bda694e91520e16cb1a3 +size 4999711752 diff --git a/model-00038-of-00044.safetensors b/model-00038-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7597724539ff0ba3b0a66b38e1e9395d5bdf9c2 --- /dev/null +++ b/model-00038-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f462c5c297a1da289e0c71e75168ef9c741e4ab693bd9d68319cad5195ff607a +size 4815146112 diff --git a/model-00039-of-00044.safetensors b/model-00039-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d1f322436d8d5b699fc673f0ebd7d4de6cca29e --- /dev/null +++ b/model-00039-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d9050f5852f4b0d7f82da8cd46b782514352bdb298eaded8766ac4a4816787 +size 4664167432 diff --git a/model-00040-of-00044.safetensors b/model-00040-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1294359e1c4c2efacc548e49fb28ad7d6d1bb28 --- /dev/null +++ b/model-00040-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403179676ef4c972b7c424c4dcfecbbf8885a614cced7f988d049a0e51bc1ce0 +size 4664167424 diff --git a/model-00041-of-00044.safetensors b/model-00041-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11b42aae9a4de895ae68901f6f61fac263e86c57 --- /dev/null +++ b/model-00041-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf065a0a9807e49f19414c324f5b7bd976b9745e46a87caa9c400291dde1c91 +size 4982917928 diff --git a/model-00042-of-00044.safetensors b/model-00042-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92aec615e7117a87fece989f41ef7c27b8f252a --- /dev/null +++ b/model-00042-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae6e2eae278ec79592c406f3463ba21142740991ed37a14e03b275330d3870e +size 4999711760 diff --git a/model-00043-of-00044.safetensors b/model-00043-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7367b63a0391f9558492e18516800c07a7647ea2 --- /dev/null +++ b/model-00043-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d102f4e12698dd079200db1b3392a53ff10854322f88ea73a7dc53a67d5577 +size 4647373592 diff --git a/model-00044-of-00044.safetensors b/model-00044-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bfafe9bd368723b6413b198f32b04efa7ca643b --- /dev/null +++ b/model-00044-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285fc834b7ef28c47041281538fcd432e1d35f14bfe1ff0445a4dd3b8824e887 +size 2483095360 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..213fcb5b0ec776f4fc21589da9fe977cb588eab3 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 209559764992}, "weight_map": {"lm_head.weight": "model-00001-of-00044.safetensors", "model.embed_tokens.weight": "model-00001-of-00044.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00044.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00044.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00044.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00044.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00044.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00044.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00044.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00044.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00044.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00044.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.55.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00044.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", "model.layers.62.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00044.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00021-of-00044.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", "model.layers.65.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.64.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00044.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.70.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.76.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.79.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.78.input_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.82.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.81.input_layernorm.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00029-of-00044.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.85.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.84.input_layernorm.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00030-of-00044.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.88.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.87.input_layernorm.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", "model.layers.92.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.91.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.90.input_layernorm.weight": "model-00032-of-00044.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00032-of-00044.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", "model.layers.95.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.94.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.93.input_layernorm.weight": "model-00033-of-00044.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00033-of-00044.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", "model.layers.98.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.97.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.96.input_layernorm.weight": "model-00034-of-00044.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.99.input_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.102.input_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.input_layernorm.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00044.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00044.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.input_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.input_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.input_layernorm.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.input_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00044-of-00044.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00044-of-00044.safetensors", "model.norm.weight": "model-00044-of-00044.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..76b88b1f4f627d29caa83b571ba889ab58bff008 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2066 @@ +{ + "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|>", + "padding_side": "left", + "tokenizer_class": "PreTrainedTokenizerFast", + "unk_token": null +}