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..073ff0dbd3cf9d152efb08491d0ec0bc0de2f531 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x308 + +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 [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/prototype-0.4x295 as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +* /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507 +* /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c +* /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c +* /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c + - model: /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507 + - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c + - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +base_model: /workspace/prototype-0.4x295 +select_topk: 0.24 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..0fcec78aaef89ed38b6a242c7405180036efc138 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set loop_messages = messages %} +{% for message in loop_messages %} +{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %} +{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %} +{{ content }} +{% endfor %} +{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fb7e20717b2a6ac86d90bd43b28a9a0d64745b7e --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "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": 80, + "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": "float32", + "transformers_version": "4.55.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..d9ce3a4d7c4009a3dcdaf86719bbd70e9469cb13 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,15 @@ +models: + - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c + - model: /workspace/cache/models--nbeerbower--Llama3.1-Gutenberg-Doppel-70B/snapshots/f083f3a89b8275e7e5329bb0668ada189f80b507 + - model: /workspace/cache/models--tdrussell--Llama-3-70B-Instruct-Storywriter/snapshots/19be2a7c6382a9150e126cf144e2b2964e700d3c + - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +base_model: /workspace/prototype-0.4x295 +select_topk: 0.24 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f506d237ee10dfd887680b705c7ac4f3be4cec4 --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eee9390926e7aaaed531e6d6b8e7905a2138ca6d528907bdabe760ad2792926 +size 4362175752 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..355aec493bc0191104029bd5cccb6e7d4fea8624 --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a56d79c003f9b03fdebdc15a5a9d83aa9ad499a2d19f9074fb91730f749c7fc +size 4202692736 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..252807e3ea58762f804a44cf8a948aee06f45ebc --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba32302c03a40e13e1556e990a0f556eef8b54c56331337c94d86e9c1f8c4e2 +size 3154150216 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d777b13df568e80fbcf165333c62fde2b01520c2 --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52eef85314b056d774c1a298ac3b0b5643b38f5fd58528a79acf7f499ffebf4 +size 4202692744 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ef3b26ff82ff9fa0f0402ef8435c35211e2a6cb --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ec7c98c8bd495e5bdc13b0be7a51cc721f564af71cc67a0cd61914fc654e09 +size 4932634344 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..37c3771b3e044518d14d4295ad3fd5c59c12b01c --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e638811080a0a0aef0f426a4c15448c18fdb40830305f8d445143f6be94bfb0 +size 4362142880 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f7754ff915647eae9e5508906e8939e1af83589 --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa00d0251a7f253cddc6b3bf964ffbfce9be91c29d4712c1627b663c0885634 +size 4932634344 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acbcb44e8702c37e938dfc6248e2530fdddf8d65 --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ce9f217d27de9d867c9b8920a7edd0b578d05c1b8052ae9d51956bc8c38716 +size 4630611336 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48ef6f1d513757e18e93b6b8e008b73920772317 --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2114eb228e3caf6bb96da6fe3db6854ec2acef44ce4ac71b9dbfbbf7d133b079 +size 4362142888 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bd110a05e30020d46efee9d9e1d45e2487af7241 --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb74ef04ffcd644bb8ebcc6621dcfd368863bbdc4a4700ef60c81ecb50ac5b8 +size 4362142880 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b76c807e91775ed12cd70e9370931c06aa080b0 --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0443485c72e483e7fd508c95b021c180ef2e9efedbe1c247ea6d79473af1642f +size 4966188888 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9995a4c98c25b7a4c2681b67f2eda90cce04ba7 --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e644e5d3aa113461d9df5f1af92d96a26842a3df8758a17f9fe85ae23efc46b +size 4362142880 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7dcfecfcfb93a70718c1707865a985477760724c --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c903cca0f050d6da84dad28008d9fdf97b943163d2b38ddf8d075e3a08ba36a4 +size 4630644216 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9401a95d146a3fd6e4885d3ee00d4685b2465800 --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73805b79dac2cb09246c39f5069950b330c3e1c04daa4436b4fbca75f3031ea2 +size 4630578456 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..065c792c943be9de1aeab995e00aa4b14d4e3bf5 --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b11a26487b0c43bda3e59a18bd0a650bb034a19190381bf7a291db4d6a67c5 +size 4630611336 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68e1e199955b5739109e640f509959a957e93442 --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671077ac910d739558d05ef6198eee7d93a86b603ad1ac775246e2cd496eea56 +size 4362142880 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eeb099e2914e74c2240acb1eabe7b33b0bcc0091 --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bfa9c910c6470fc77a65d1e6c51b8e69573be96cd4b88fecff8e8f90f14ab6 +size 4966188888 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..548c270f4bb54cbd3b9b657fc8c2cfb443103cda --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15e1f7b384f39ff432c780ad243cb9de4d336724b9d28a6576aeed3e848ca24 +size 4362142880 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99b0da2a9aee7c62c8d5a3c1cb0a0b38a425a397 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c91ea1f37d3abcd8ebd9d73ed5450c0a69807d5eca05ce0cdfbf5c56afbfcd +size 4362142880 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01d252299131c26bd87c36a8b8fd0e3c7d10c76c --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed8f5e630051053d320fab8b53a300fa0a26e05d9af00ee39d3e43f7d66ed8e +size 4966188888 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca85390db48923bd5c39c7f2e3a8cd57d14c7208 --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff468ee280b5d260d3acd65c8c25a4aedeab28a13f54eb3a13ad5624c5a6d8ac +size 4362142880 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6539ddc8a51ab3d4bf75da512c39e5972b8231e3 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50202e7b87a618329e1dd1b2433530c0744d9b3632cdc47b4bf4c10a6bb1fd6 +size 4362142872 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd1f23c0e21c4e403493d405a4bd15263e5170c0 --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e80832205ea6d9f17e6ede3af7cb544346dcdabb6893acfd198f68076c7a930 +size 4932634344 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e0761f596c81ee3515f1678c7166ac11a56b3f6d --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a08e5ff459e79011bbe0cfdc26bf0eb51a518081c6a1856023bcf00ad6da4fc +size 4362142880 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb83072f68f064e7f6a96583f0498d28ed20ee99 --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c98e64fa76633a0a8be58ecdaea79019a342a0d698d83b9703310c08d39e168 +size 4932634344 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..186abdbff35eafbb969d066c7f597097d139714d --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6039e34b26b6a4e197ad93a6bf4fb4c6fcbe6eae9347e30e0b299d463d8561 +size 4362142880 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce9ca8074962778e66c0e7cf8af24b6b33d139d1 --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0555cf1c695903ac7f27a3e59296da63d8c5d7493f671dc0296ed70030ad8fd6 +size 4630644224 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dd1e74692f9e25fe8f30db6e3385db548b34d6b3 --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b447114f514d6fd5743abf2325ae7766541aea078065673fbb347f73d10c4cf7 +size 4630578448 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c7429a40e93b1548f54099dbfd415558ea4d2b9 --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523f244e4b1a274a32fb429b703ffcee5072202963825f8bd959d01babbe9614 +size 4630644224 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dfa97c60fba028d4c32ae5376a8ba6a84c335841 --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63beb61995362731cd41b569dff8b22b0ca622b0875161af895f153e73dbaed3 +size 4630578456 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98280356b88ed109dee25a44f9fef432d58284e8 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:335c4c0b5df369ec31bd858d4dc031e6d3452f4e833d72a84137843516e857e8 +size 4630644224 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4575cf7d41c59e2e78d26ef9589da6a1dad863ff --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becec4ec8bf726dbf3dfccc16f43b3dee85958e8d25ec914d22470a31df3a853 +size 4630578448 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..343e948e4a859954a7b7c09c315e08e408cd1e71 --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5c229ab0cff1c48fe592e8b7c301d93ab3467217a27bbff379ced029a413f9 +size 4630644224 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..314e50b19e170130656dcef0015724f686b09a92 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a030070642a4146c47dfd406030e85ae7b1105215828ce6eec6b34983e2a4e +size 4362142880 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..842904bb9b5ae23d675e5748968e9e0b5db05a67 --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b888fc6c58bbb74b6078e6630395e15f73123412a35c93d1ddb65f76290375 +size 4932601448 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..981633a47086e09b6f66425543b65a006af7a4cf --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e90bcb0e582ea30a2b544a40a38fb406eca6681ab181d664dda692c5926050 +size 4362142880 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9165429e76e820fa160864a3e0e0cb7df17f06ec --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb18d9d5f4a1940a56b3435c60294ed5ccefa3701283206b0c375cb22cb46af +size 4664198768 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f40d584695d5ee884a90ca0ac59021cc15062cdf --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d06d81c4ac1530de3d5fba08aaab4a4801616f7e45b9f4cf1dcb9d2287e1c52 +size 4362142880 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..982813b82fc47ff683df20ad6576f51307ad472d --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6337e64ddc77ffb534011926dfda8d646e3518ced8dc75f59e9a42ab6727eaf1 +size 4932601456 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94e0e9788feb1ef90e16f4e0e6336428c9efab5e --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a60b62e7d1a3c4fcad17120eeee46f84ebaf6a3bc4fb59fbb378e71b7c54708 +size 4362142880 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb9d4a4d6db5da8fedafc72ff259094f638ceed0 --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00574e1b2f07ffa7f7dd23e64f074b842100dc747ef36086dad177da5568f411 +size 4664165888 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..81c97744deb660e1c26d18225b3bf18be11b4b1f --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62ae55e7bedc902629adba2eae3012154fd59b015c6a5d84a6be9dfed211438 +size 4664165880 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c203779a95e5152af0769d6979d60e7aaa0943d --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a885325052b232f3d18ef0570bd2b104f73420b4b5606741c8da4fa24b9858 +size 4362142880 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfd8e3a9a3fce6a696af59e12aec166da89ffd0e --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb81e34805c7cc5f3d03ab0a24d731f71ca55efdb564c89f905420d87d52120 +size 4932634344 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..113425706ef6bdc4e2a4aef28032cee9c63b70c5 --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b97444f235a3e015cb0b403627553dad878fbd4ac82c03e0494f70ceaf344c +size 4362142880 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3ef26b5cb7c63ab868311cf2dd5c9fd70a1cc9c --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c179a9bfd41931c196147306fb620acccd4d4f103595d9c38fb6498e3b21371b +size 4362142880 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..087dcce205ef054a13aa0c05f1a133b514162227 --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322490e60d53fa0e96854b8cc9bf34695580df0f31c568188b3e72b00ca42b47 +size 4664198768 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b479c5c6be13f4a30bee3468dcce8e2bfd23e4b9 --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de537f7f7228fcad8417f63ecb097bd40e807783e50a9914c5825664a6d7b866 +size 4932568576 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98efc7343ac1c0412bf0d9046310a583c892c398 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac88ce95b0dec602d8a4471f2d72a47ed76c1fb27ea05c34977a509220a4dfa +size 4362175760 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1d2957018d7d8ee5364afdb2fbcb628dafbca94f --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214c357db32999db7c95879f76ed2b793d3ea7c789564aba8d81181fadf79f53 +size 4362142880 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..125f1604f7f7dcd7937c26f2622598dfc0b7d248 --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825347cec0eba60062e4d05db13d1a1952e53f1aaaa652d99ca826e64cd9185f +size 4966188888 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ea3c8fce816de826166f0ef467c315b28c614d8 --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2b0cc4ffe7f0942a3f7d81a138d014e4f2919ce046479929ca9b2d1838d0aa +size 4630578448 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9098d89ec1df939c88758a045664309ba8d55ac --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d6775b4d537b9c9325f63a2335ccead5301fa891fdef1ec29e1ef1b54145ce +size 4362175760 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7fac4b3bc6cbb712e9bbfb51b9338024034ed09b --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbf1e8968dbfa3ca52afe8b9802e72d441d24c2738a9700368da3e7e3c0ce54 +size 4362175768 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d72d40c224dd3cfcf09257c9f6bbd2783412546 --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0dd63baf4689ae74db81de96815416af7a943f90f0ad7d7078743c59814ddf4 +size 4966156000 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ead66132a03b33078ddd3994c7825b95867f573 --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c76723b52f6f85d6047b2529efaa24ee2aa97b8513ce41be7d6469f96d7546 +size 4362142880 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba12a09c8726a0df131219212564d71b08e02c87 --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7946db5f1167757d39152f46ac7a6f449fbcecaf3d5b8f8de276f4ce003e62 +size 4362142880 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93591654ce9b7019b73b6509b80ed460d32cf65d --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b975e1eb5572c5c98832c2310bca280d2feeb7bd6f074a4bc08c3a2e8ea3c69 +size 4966188888 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5234f24ad9df3e23a997034161c578500ff360f --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4956fc15c3313de1b61b0685c1686632bbd0df93e16cb4a99150f632be401559 +size 4362175752 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b832a0c3f4100eda12f687bdab5d5c796855967 --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165806bb51dbbbd276aeaee00230de7f8286641b6a7e79c97b7cf5b03d01c6d9 +size 4697687560 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0c473b99da9a16afa999ccbc7e0ab9892dcf367 --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae50c200c581951f8548cfb4127a8aa6763758f2dd991ee99f3eaa0bf6367fb +size 4999612024 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..652c81975b1222d8f258adc3b9c5030676ca0103 --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc0cc90b1a2448ddd3fce996ecfaca5750efb9cba0394f6ae7637d5e2645d40 +size 4060087808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..3a96c9510e573ca75bb857f403a5951573ef14b6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00062.safetensors", "lm_head.weight": "model-00002-of-00062.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00062.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00062.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.embed_tokens.weight": "model-00004-of-00062.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00062.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00062.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00062.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00062.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00062.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00062.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.12.input_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00062.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00062.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00062.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00062.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00062.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00010-of-00062.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.input_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00062.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00062.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00062.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00062.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00062.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00062.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00062.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00062.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00062.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00017-of-00062.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00062.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00062.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00062.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00062.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00062.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00019-of-00062.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00062.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00020-of-00062.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00021-of-00062.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.input_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00062.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00062.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00022-of-00062.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00062.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00062.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00024-of-00062.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.input_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00025-of-00062.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00025-of-00062.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.37.input_layernorm.weight": "model-00025-of-00062.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.38.input_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.39.input_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00027-of-00062.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.input_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.input_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00029-of-00062.safetensors", "model.layers.42.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.input_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.input_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00031-of-00062.safetensors", "model.layers.45.input_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.input_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.input_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00033-of-00062.safetensors", "model.layers.48.input_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00034-of-00062.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.input_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00034-of-00062.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00035-of-00062.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00035-of-00062.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.50.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00036-of-00062.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", "model.layers.51.input_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00036-of-00062.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00037-of-00062.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.52.input_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00037-of-00062.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.53.input_layernorm.weight": "model-00037-of-00062.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00038-of-00062.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", "model.layers.54.input_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", "model.layers.55.input_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00039-of-00062.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00039-of-00062.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", "model.layers.56.input_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00040-of-00062.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00040-of-00062.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", "model.layers.57.input_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00040-of-00062.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00041-of-00062.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", "model.layers.58.input_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00041-of-00062.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00041-of-00062.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", "model.layers.59.input_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00042-of-00062.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", "model.layers.6.input_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00043-of-00062.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", "model.layers.60.input_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00043-of-00062.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00044-of-00062.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.61.input_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00044-of-00062.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00044-of-00062.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", "model.layers.62.input_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00045-of-00062.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00045-of-00062.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", "model.layers.63.input_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00045-of-00062.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00046-of-00062.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", "model.layers.64.input_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00046-of-00062.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00047-of-00062.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.65.input_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00047-of-00062.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00047-of-00062.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.66.input_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00048-of-00062.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", "model.layers.67.input_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00048-of-00062.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00048-of-00062.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", "model.layers.68.input_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00049-of-00062.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00049-of-00062.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", "model.layers.69.input_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00050-of-00062.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", "model.layers.7.input_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00050-of-00062.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00051-of-00062.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", "model.layers.70.input_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00051-of-00062.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00051-of-00062.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.71.input_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00052-of-00062.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00052-of-00062.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", "model.layers.72.input_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00052-of-00062.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00053-of-00062.safetensors", "model.layers.73.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00053-of-00062.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", "model.layers.74.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00053-of-00062.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00054-of-00062.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00054-of-00062.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00054-of-00062.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", "model.layers.75.input_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00054-of-00062.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00055-of-00062.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", "model.layers.76.input_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00055-of-00062.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00055-of-00062.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", "model.layers.77.input_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00056-of-00062.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00056-of-00062.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", "model.layers.78.input_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00056-of-00062.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00057-of-00062.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00057-of-00062.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", "model.layers.79.input_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00057-of-00062.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00057-of-00062.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00057-of-00062.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", "model.layers.8.input_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00058-of-00062.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00058-of-00062.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", "model.layers.9.input_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00059-of-00062.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00059-of-00062.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", "model.norm.weight": "model-00059-of-00062.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00059-of-00062.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00062-of-00062.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..c68051fe3c4d23234a59316bc52d21f6e3a4182c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "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" +}