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/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..1a1214b84c80740146592a489168d08b347d7f2d --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +base_model: +- Doctor-Shotgun/L3.3-70B-Magnum-v4-SE +- TheDrummer/Fallen-Llama-3.3-70B-v1 +library_name: transformers +tags: +- mergekit +- merge + +--- +# merged + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the Passthrough merge method. + +### Models Merged + +The following models were included in the merge: +* [Doctor-Shotgun/L3.3-70B-Magnum-v4-SE](https://huggingface.co/Doctor-Shotgun/L3.3-70B-Magnum-v4-SE) +* [TheDrummer/Fallen-Llama-3.3-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-70B-v1) + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +dtype: bfloat16 +merge_method: passthrough +modules: + default: + slices: + - sources: + - layer_range: [0, 20] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [10, 30] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [20, 40] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [30, 50] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [40, 60] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [50, 70] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [60, 80] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..e70ca59c85789e08d18b8c85d854c985d730b8f6 --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 140, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.53.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..9cf68744f69035ee8cabbfe02fc6e9a26d3b31b8 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,26 @@ +dtype: bfloat16 +merge_method: passthrough +modules: + default: + slices: + - sources: + - layer_range: [0, 20] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [10, 30] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [20, 40] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [30, 50] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [40, 60] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 + - sources: + - layer_range: [50, 70] + model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE + - sources: + - layer_range: [60, 80] + model: TheDrummer/Fallen-Llama-3.3-70B-v1 \ No newline at end of file diff --git a/model-00001-of-00050.safetensors b/model-00001-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a025c8ad5602c9cd7c0858a70682c416eec8a8e --- /dev/null +++ b/model-00001-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985f23c68602f9dcd77c92f0049127d865c0e4fb02dfac529b08310ef06e9e0f +size 4672471504 diff --git a/model-00002-of-00050.safetensors b/model-00002-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..708011723ecc0cc94a6641d87fd29647d801b93f --- /dev/null +++ b/model-00002-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3e4e6536fa129bb68b906f2acffd5adb2dcda5004d83f37330560f85e79231 +size 4831922704 diff --git a/model-00003-of-00050.safetensors b/model-00003-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d26d1a177ae6822c3f901e50a7e9df31b9e5d6c4 --- /dev/null +++ b/model-00003-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34cd210934d16aeee43cccc4a722241a0e45f1b775ee89a6c4e0a46b863bcb2 +size 4966190768 diff --git a/model-00004-of-00050.safetensors b/model-00004-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b388b252108b0b8414397925466a68c71fb9aeb5 --- /dev/null +++ b/model-00004-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1c39bc0721309c375fe60fc25f54697c15bf7aca80667ec17fd7e607b5706b +size 4831906224 diff --git a/model-00005-of-00050.safetensors b/model-00005-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e9884ed37bef809bb670aa5c98011c6843e7fd4 --- /dev/null +++ b/model-00005-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cc4763d44bbe233a46035071c6160c8db6e2d6d661c5a4cdc4ae11e055d95ba +size 4999711736 diff --git a/model-00006-of-00050.safetensors b/model-00006-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b6e37261694f7ef3997e454393f83e831cc7df2 --- /dev/null +++ b/model-00006-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566bcd06968440b25f2041f51a6edb9fe9de22049399bc4c8194702e0fbcf9ad +size 4798385256 diff --git a/model-00007-of-00050.safetensors b/model-00007-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d75bbe70c7b12c9efdc4b8e2e2befdbe0f1a9910 --- /dev/null +++ b/model-00007-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2931e0450035d1c45702e840695526ad5d1b91106c423fb44e1b2b17aa5972d8 +size 4831906216 diff --git a/model-00008-of-00050.safetensors b/model-00008-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f640cc7f971abff924611fa24be03a09d7321bb --- /dev/null +++ b/model-00008-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac1bf90ae842da254b2149b38dff591ed3a0fd7fb6312bde38d8f3ff08a0ecb +size 4966190760 diff --git a/model-00009-of-00050.safetensors b/model-00009-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..573d515c4823244e98117c48315e620fc4bd3ccf --- /dev/null +++ b/model-00009-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf7bdbe8c9e59702a294cd2a17a459a668fceb76a9a13d7c14d6323be6c9ae0 +size 4664167408 diff --git a/model-00010-of-00050.safetensors b/model-00010-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b143bae518707e011e899d1fb4116764aeb3aaa4 --- /dev/null +++ b/model-00010-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f48d8c4cce70d365334b59275235650c8486e63274e4c8c30a5c5dcbfa3cc2 +size 4831906224 diff --git a/model-00011-of-00050.safetensors b/model-00011-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d9ae4246ac3717efb130e618dbacb0f83b1c439 --- /dev/null +++ b/model-00011-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ace9f8e9f1b4c4624af0e9d946305d7c6f4aa38c8c367600358057405c9dfb +size 4999711736 diff --git a/model-00012-of-00050.safetensors b/model-00012-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12d42d0a2b34624a272641fc7c060e8fcd65d596 --- /dev/null +++ b/model-00012-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fbafdb169e9bc9f0a84b11487a006e4f1206138cd165581b946bae69fea75f3 +size 4798385256 diff --git a/model-00013-of-00050.safetensors b/model-00013-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c251ec68807feda76772d1c445e0137620c57f7 --- /dev/null +++ b/model-00013-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bbf4e8110390b93a846bfe351e685db9d7e94b9355c13bf8c9a6abb7d14b52 +size 4831906216 diff --git a/model-00014-of-00050.safetensors b/model-00014-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76eca77140516f7ac7161c010642764fb8879127 --- /dev/null +++ b/model-00014-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f04990950547023c8cf3beedc62933cbdc81e7bb8675141cb1453ed753ca2e2 +size 4966190760 diff --git a/model-00015-of-00050.safetensors b/model-00015-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b1406f5c46e9a2ab562abdcdd6ac8c02ef73f8b --- /dev/null +++ b/model-00015-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a0ca099dfe261b547b90746335cf95a20478a565078af1dd32bba90c09d305 +size 4831906224 diff --git a/model-00016-of-00050.safetensors b/model-00016-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e99ce04c329c5e63d3fdf99d6a996979edbe51d8 --- /dev/null +++ b/model-00016-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254a43eca3ce92b56df1ea88d07c35dc53d37f2ecf1e92e46dafd982b507110a +size 4966174264 diff --git a/model-00017-of-00050.safetensors b/model-00017-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf48d745a4e7b712c5a50a86e6f984c3d8aab658 --- /dev/null +++ b/model-00017-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fc10a5144e3491f6bb854a446a50bd66e031fb2daad50e53d40d10807cfadbb +size 4966140568 diff --git a/model-00018-of-00050.safetensors b/model-00018-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..578167e5b447fcfa1b0081eefaf596dc8c41629d --- /dev/null +++ b/model-00018-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f409317ff8ec4368171d1b9ea1631ae863c2db64177057cf619ae2c21c9c94c +size 4999711720 diff --git a/model-00019-of-00050.safetensors b/model-00019-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7380c2e2fb1d335c6b24a6bc8598d68d9bc9f9e1 --- /dev/null +++ b/model-00019-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bff6f87a0f434047255a0076404e6ec1f82aa328671c77c3aa5df337eb5e864 +size 4999711736 diff --git a/model-00020-of-00050.safetensors b/model-00020-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eeb744e9bd8aeea740c533ee65d663d853a47085 --- /dev/null +++ b/model-00020-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e28e2d1382ea848660f7a38ec6d08f12a79fe704aa9a40d9121caa63de86355 +size 4798385256 diff --git a/model-00021-of-00050.safetensors b/model-00021-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f1b6cd73da8ab40416f48e9e1c902ae60017a28 --- /dev/null +++ b/model-00021-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3407c26b84eb8d4e35628ff543892e3bc9f6b9049a4b69126d671824ea3db745 +size 4831906216 diff --git a/model-00022-of-00050.safetensors b/model-00022-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4549699c86ca2171b17b0dac43aa60ae32d85e71 --- /dev/null +++ b/model-00022-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fc5e77184e347c6132c28aa875af51c15ac7bd7d95bcdce4c257ea5e7784f2 +size 4966190760 diff --git a/model-00023-of-00050.safetensors b/model-00023-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e215568c5af778673da7d9e5caa695c1df9a326 --- /dev/null +++ b/model-00023-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f3e67db0cf381bd84aefc342b062e582b8e8510bbfcb40c1d48d56ee286fbc +size 4831906224 diff --git a/model-00024-of-00050.safetensors b/model-00024-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73252cc8fc4e79e7f9aad7eaa54abc7cce1f555e --- /dev/null +++ b/model-00024-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:266f992ef72546842d3f9578662751c9c9c662a1e25b83521264b43a188d3505 +size 4664167400 diff --git a/model-00025-of-00050.safetensors b/model-00025-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b55825b5e2ce25d9f8f947290b43233ffd7a30d9 --- /dev/null +++ b/model-00025-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a5a5b980e1cccb6c516e2eb3f41c0ec5ebd7b20c09dbe8df6b6c66b73b4b16 +size 4999711736 diff --git a/model-00026-of-00050.safetensors b/model-00026-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71552ac5b0bbb9a129c4e5db3d72c530e32bd011 --- /dev/null +++ b/model-00026-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12af4bad84a456825b607e3afa55d06bd63bba0ec09625b5c92fbf93e5b5451 +size 4798385256 diff --git a/model-00027-of-00050.safetensors b/model-00027-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..964697f4e69e16828e2df1a0060e7638f21c5965 --- /dev/null +++ b/model-00027-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f35b2ca344b5e815384efe0176fb7796f2620f64098dc32ba5eba6a98b5bd9 +size 4831906216 diff --git a/model-00028-of-00050.safetensors b/model-00028-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa4e2c7b2e80f959f5de9f582ab1ca1aca2e72cb --- /dev/null +++ b/model-00028-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b0088a280db6a2c50bebf0c76bc6ea93515f501342a07d061a16598b934087 +size 4966190760 diff --git a/model-00029-of-00050.safetensors b/model-00029-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4180db99b0f954aba1d8523550039953a8403e4 --- /dev/null +++ b/model-00029-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3972d4273dfeb4e717fbd691ac20f0de68b5c897899a58a64a508131334e7b1 +size 4831906224 diff --git a/model-00030-of-00050.safetensors b/model-00030-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84e09b94669b5ebac6fd10c94efea2d4b21bbdc8 --- /dev/null +++ b/model-00030-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd1000a816e9515f56181c821e7a5c9cf8a6dd2b9b3a90cbd9ad9bd3efec2ee +size 4966190768 diff --git a/model-00031-of-00050.safetensors b/model-00031-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7ad2f5fc4d4cc3a3470c1dd9ed6d46d03ecab27 --- /dev/null +++ b/model-00031-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf371600689352acf947c549cf857f122db8b3a235b99271210c66c584460c6f +size 4982901392 diff --git a/model-00032-of-00050.safetensors b/model-00032-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..869926380d04e1f724222c1f3fcece124491f818 --- /dev/null +++ b/model-00032-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9adbf77d7036bac70f7327b6586bfe6356ecf89b5746c359a55c21f813dc10 +size 4982934392 diff --git a/model-00033-of-00050.safetensors b/model-00033-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee3c6ac5a32f7d6d7e8831d187078d8e6ba40eaa --- /dev/null +++ b/model-00033-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65d0f2b512ec08add6ec7022f748063b7a25e4357a7d91fd81607141ae7796a9 +size 4999711752 diff --git a/model-00034-of-00050.safetensors b/model-00034-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..319ca63fc3d921acb6e0b4b5f4b2b62cf6f871c3 --- /dev/null +++ b/model-00034-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdba4b8c64fd184121facb9c86c05972284f515644153f7dfce6cf250a3320f1 +size 4798385264 diff --git a/model-00035-of-00050.safetensors b/model-00035-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bb3f1b66525583a77c70a6e3170fdc1f94e0414 --- /dev/null +++ b/model-00035-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bd737fd4bcc9c74e1266b6bb7dab7b5c3eb4c78ec0fc10d6b367f2b1d4b2b4 +size 4831906232 diff --git a/model-00036-of-00050.safetensors b/model-00036-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33dd20c84d5b6a8677b051b05ee9ecae361915f8 --- /dev/null +++ b/model-00036-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94723fd9a9c0aab982cf419cd81a569d7e4142a4056e37901e471037f0b68596 +size 4966190784 diff --git a/model-00037-of-00050.safetensors b/model-00037-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebdc3436c7f41c4f7c597ab4aa6b41e54ade42fd --- /dev/null +++ b/model-00037-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda86d13b294b6b175873138a0023fddd955097ea76fa29c5a6fabe48a232eb5 +size 4831906232 diff --git a/model-00038-of-00050.safetensors b/model-00038-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bd53f3d0ac8e1ef169e0dd7a50c3a97fcbd3651 --- /dev/null +++ b/model-00038-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fdb45f492afe4408f51d9f0986ca2207829e3992b7efbd3ba9786cacf9bb3bf +size 4966174288 diff --git a/model-00039-of-00050.safetensors b/model-00039-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6350e8cbe87757ddb94262cb86a78f7102b21b99 --- /dev/null +++ b/model-00039-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f26689a36e74ef2cc074895057845f387cb85371c7da533ff996e194589abe2 +size 4966140568 diff --git a/model-00040-of-00050.safetensors b/model-00040-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cab5e09d40ace0a9f6f4c8d797c16ec207eaaa41 --- /dev/null +++ b/model-00040-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a234b6df0f7ce898b2d6491420fdac05f0249611fe70514b066dd3b28b438efe +size 4999711752 diff --git a/model-00041-of-00050.safetensors b/model-00041-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04d3b0b0fa8a0b4009227e0bb50c687ad51d52ec --- /dev/null +++ b/model-00041-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a50518cb3fbc9299b1b2c7768b56b800a4c88c17140fe745817683fd3e36457 +size 4999711760 diff --git a/model-00042-of-00050.safetensors b/model-00042-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2250eb7dac37443285f497365883aa504527d2b --- /dev/null +++ b/model-00042-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e2dbafba18a183670453ef3220d7c268ee90cb6b8b5f7bbebde7024dbdd544 +size 4798385280 diff --git a/model-00043-of-00050.safetensors b/model-00043-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b0b2e173325f4b19fe7b64710511ea71b341959 --- /dev/null +++ b/model-00043-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79025c441347ada806c5ab87b12f1f19019e3af97b3a961698d8225016a993cf +size 4831906240 diff --git a/model-00044-of-00050.safetensors b/model-00044-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cda24e1a606a91f80e2de826f0616a38811e3b8 --- /dev/null +++ b/model-00044-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a391df627c02c26025a73c4f1d7f3ffe47df6d8bf08d3b0eb4a2215ef918fe73 +size 4966190792 diff --git a/model-00045-of-00050.safetensors b/model-00045-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..28d8b6d8c6dac162791cd54ed2d9e40eebdc3e1f --- /dev/null +++ b/model-00045-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6933cf1d8711b92dc1dc9199326a9f54a6766acd91b0744223c3de942f9ef9d0 +size 4831906240 diff --git a/model-00046-of-00050.safetensors b/model-00046-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d0370d10f609129487de7fabc34d564f0a1bc9d --- /dev/null +++ b/model-00046-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca5e0f3ebe8757407f5d5708d3ac6cf66ead4dea36dfe654a959be52a3c5a042 +size 4966174288 diff --git a/model-00047-of-00050.safetensors b/model-00047-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26892d746b48cd31735e99d45918a4578283d358 --- /dev/null +++ b/model-00047-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21463b4f1ae8f966aa6b27b85caf9b9dac2dee3ef5a32db85ad563e66ca939d4 +size 4982917928 diff --git a/model-00048-of-00050.safetensors b/model-00048-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d3db0f3b58994cc60352fc58d2ba70b70d3f4a8 --- /dev/null +++ b/model-00048-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f443e932621cf71de65cd7eddeea87d3fb050b255df5f2142a1b93180148fe6 +size 4999711760 diff --git a/model-00049-of-00050.safetensors b/model-00049-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2a551480e4cb0f0f6b501525cfa3207bd90b022 --- /dev/null +++ b/model-00049-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fa9ea7b292c33bb17524e1fb4d3eb8caccc2f1f8286c28f51c1b08c7a9b379 +size 4647373600 diff --git a/model-00050-of-00050.safetensors b/model-00050-of-00050.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d22b56e62e84b7ea30436c0cec9859ce04ebdb82 --- /dev/null +++ b/model-00050-of-00050.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7b9dad3049c55201ae393e9933e64aba6dae2bb10a0796702dcfd25840035a +size 4194405216 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..89ea6a8826e069a2e36885134c278f7f2ecf2798 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00050.safetensors", "model.embed_tokens.weight": "model-00001-of-00050.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00050.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00050.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00050.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00050.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00050.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00050.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00050.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00050.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00050.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00050.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00050.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00050.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00050.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00050.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00050.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00050.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00050.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00050.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00050.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00050.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00050.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00050.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00050.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00050.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00050.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00050.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00050.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00050.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00050.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.input_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00050.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00050.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00050.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00050.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.44.input_layernorm.weight": "model-00012-of-00050.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00012-of-00050.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00013-of-00050.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.45.input_layernorm.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00013-of-00050.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00013-of-00050.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00050.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00050.safetensors", "model.layers.37.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.47.input_layernorm.weight": "model-00014-of-00050.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00014-of-00050.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00015-of-00050.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.48.input_layernorm.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00015-of-00050.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00016-of-00050.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00016-of-00050.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00050.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.input_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00017-of-00050.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00017-of-00050.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00018-of-00050.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00050.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00050.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00050.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00050.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00050.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00050.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00050.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00050.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00050.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00050.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00050.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00050.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00050.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00022-of-00050.safetensors", "model.layers.58.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.68.input_layernorm.weight": "model-00022-of-00050.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00022-of-00050.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00050.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00023-of-00050.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00050.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.80.input_layernorm.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00024-of-00050.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00024-of-00050.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00025-of-00050.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.input_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00025-of-00050.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00050.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00026-of-00050.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.83.input_layernorm.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00026-of-00050.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00027-of-00050.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.84.input_layernorm.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00027-of-00050.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00050.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00028-of-00050.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00028-of-00050.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.86.input_layernorm.weight": "model-00028-of-00050.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00050.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00029-of-00050.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.87.input_layernorm.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00029-of-00050.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00030-of-00050.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00030-of-00050.safetensors", "model.layers.79.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.89.input_layernorm.weight": "model-00030-of-00050.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00031-of-00050.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.input_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00031-of-00050.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00032-of-00050.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.101.input_layernorm.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00032-of-00050.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00032-of-00050.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00033-of-00050.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.input_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00033-of-00050.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00033-of-00050.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00034-of-00050.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00034-of-00050.safetensors", "model.layers.94.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.104.input_layernorm.weight": "model-00034-of-00050.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00034-of-00050.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00035-of-00050.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.105.input_layernorm.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00035-of-00050.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00035-of-00050.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00036-of-00050.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00036-of-00050.safetensors", "model.layers.97.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.107.input_layernorm.weight": "model-00036-of-00050.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00036-of-00050.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00037-of-00050.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.108.input_layernorm.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00037-of-00050.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00038-of-00050.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00038-of-00050.safetensors", "model.layers.6.input_layernorm.weight": "model-00038-of-00050.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.input_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00039-of-00050.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00039-of-00050.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00040-of-00050.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.122.input_layernorm.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00040-of-00050.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00040-of-00050.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00041-of-00050.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.input_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00041-of-00050.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00041-of-00050.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00042-of-00050.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00042-of-00050.safetensors", "model.layers.115.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.125.input_layernorm.weight": "model-00042-of-00050.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00042-of-00050.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00043-of-00050.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.126.input_layernorm.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.down_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.gate_proj.weight": "model-00043-of-00050.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00043-of-00050.safetensors", "model.layers.126.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.126.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.126.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.gate_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.mlp.up_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.127.post_attention_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.k_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.o_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.q_proj.weight": "model-00044-of-00050.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.127.self_attn.v_proj.weight": "model-00044-of-00050.safetensors", "model.layers.118.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.128.input_layernorm.weight": "model-00044-of-00050.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00044-of-00050.safetensors", "model.layers.128.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.mlp.up_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.128.post_attention_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.k_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.o_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.q_proj.weight": "model-00045-of-00050.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.128.self_attn.v_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.129.input_layernorm.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.down_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.129.mlp.gate_proj.weight": "model-00045-of-00050.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.129.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.129.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.down_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.gate_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.mlp.up_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.post_attention_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.k_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.o_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.q_proj.weight": "model-00046-of-00050.safetensors", "model.layers.130.self_attn.v_proj.weight": "model-00046-of-00050.safetensors", "model.layers.131.input_layernorm.weight": "model-00046-of-00050.safetensors", "model.layers.131.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.131.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.q_proj.weight": "model-00047-of-00050.safetensors", "model.layers.132.self_attn.v_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.input_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.down_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.gate_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.mlp.up_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.post_attention_layernorm.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.k_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.o_proj.weight": "model-00047-of-00050.safetensors", "model.layers.133.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.133.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.134.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.o_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.q_proj.weight": "model-00048-of-00050.safetensors", "model.layers.135.self_attn.v_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.input_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.down_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.gate_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.mlp.up_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.post_attention_layernorm.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.k_proj.weight": "model-00048-of-00050.safetensors", "model.layers.136.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.136.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.137.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.mlp.up_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.post_attention_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.k_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.o_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.q_proj.weight": "model-00049-of-00050.safetensors", "model.layers.138.self_attn.v_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.input_layernorm.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.down_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.gate_proj.weight": "model-00049-of-00050.safetensors", "model.layers.139.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.139.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.input_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00050-of-00050.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00050-of-00050.safetensors", "model.norm.weight": "model-00050-of-00050.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..41cd8d1ca52c3fc5feaf8445ca922b27f8e8ea8b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}