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..d879b6a9a3456fa6444420bcd8f731c17a59d85f --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x330 + +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 [Multi-SLERP](https://goddard.blog/posts/multislerp-wow-what-a-cool-idea) merge method using /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c +* /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + +### 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 + parameters: + weight: [0.5] + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + parameters: + weight: [0.5] +base_model: /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce +merge_method: multislerp +tokenizer: + source: base +chat_template: llama3 +parameters: + normalize_weights: false + eps: 1e-9 +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..7478572fe0bca0db1cf4be646934093eb6c74641 --- /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": "4.55.2", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..544a97381228691fd414734063bca0c91f02da1e --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,18 @@ +models: + - model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Diamond/snapshots/a7dfb66b4469a4c9ca07ff28bccc73a44797e76c + parameters: + weight: [0.5] + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + parameters: + weight: [0.5] +base_model: /workspace/cache/models--deepcogito--cogito-v2-preview-llama-70B/snapshots/1e1d12e8eaebd6084a8dcf45ecdeaa2f4b8879ce +merge_method: multislerp +tokenizer: + source: base +chat_template: llama3 +parameters: + normalize_weights: false + eps: 1e-9 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00063.safetensors b/model-00001-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b8d01a0de98370ea3b18b6ccd89e552a5342249 --- /dev/null +++ b/model-00001-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02131f4ad7ab691d46a85ff7e0ee1a547cdb0cfbcd6666d19977038df3aeb6d +size 3422618656 diff --git a/model-00002-of-00063.safetensors b/model-00002-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4da60b5e8d804da762b2bb7b7ea4d7019945dc68 --- /dev/null +++ b/model-00002-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c53355423513ecf3bf2e80a556c503bb38ff39c4de6845ea99baa537f26b3ff +size 4202692736 diff --git a/model-00003-of-00063.safetensors b/model-00003-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..09b06461157885374d5035d9acd00277bc4361e3 --- /dev/null +++ b/model-00003-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ccb4a0dacca456cc4181babffd958d7ec0162edf4e934b4a5e7316b0dde751 +size 3388998352 diff --git a/model-00004-of-00063.safetensors b/model-00004-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..895ec7680e3b830409737f902aa7b96f9a6529ca --- /dev/null +++ b/model-00004-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bcf50cd75df3ec7ba4b2632b94cc0a04d255bfd18fb074f3455cc23a0c0f8d +size 4202692744 diff --git a/model-00005-of-00063.safetensors b/model-00005-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e76f2588b82f58d177365ea3019e834890b728f --- /dev/null +++ b/model-00005-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde18799a2ede73ff06094b385bedfb6427026c341ad3975e3c772cc9a7ab134 +size 4194502464 diff --git a/model-00006-of-00063.safetensors b/model-00006-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..35bc14b3b499710149705a3c3c662f56bf7ab2d3 --- /dev/null +++ b/model-00006-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591df0013cec57208318382d435399d7177b764a954fd08397ddbda33b6f13f4 +size 4865459480 diff --git a/model-00007-of-00063.safetensors b/model-00007-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..278fec0291463ea1a46bc94c229d1bca60347ce6 --- /dev/null +++ b/model-00007-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c454bfea3e0436fcc922be4b09a2f2b3a704cc21cbeb7f0ef529f03244cdfc8 +size 4596958144 diff --git a/model-00008-of-00063.safetensors b/model-00008-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a760dd17541c6b431b258cdabc2565323ada32b --- /dev/null +++ b/model-00008-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d950ff53bbe3ed06a085be940e38bbcdbf970398cc5d32040411f98866eae94 +size 4228057024 diff --git a/model-00009-of-00063.safetensors b/model-00009-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bdaf7d1aaa4fe90e4c27c5e8796ac64f35dde7b2 --- /dev/null +++ b/model-00009-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8025ddd6dff058f5b6eb01054d16a2a20450c4272f0bd917dc8ea33864487dd6 +size 4865459480 diff --git a/model-00010-of-00063.safetensors b/model-00010-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a50bbb81c1da0a8533bfaa4e7c55f437555a3cd7 --- /dev/null +++ b/model-00010-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e486d8711d117c337817ac0f31224fbe22a2c26b3bba6d2aa11d1f8ace62fdff +size 4596958144 diff --git a/model-00011-of-00063.safetensors b/model-00011-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9f25d4ccaab110ed9e9c10b73b0739ded5b25d9 --- /dev/null +++ b/model-00011-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b754b402024cf082b0fc0cec5058a85a9e268c80198333d87904c9249f0227 +size 4228057024 diff --git a/model-00012-of-00063.safetensors b/model-00012-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15bcf194eaf5ce4d7495dcee7849c941b304d17a --- /dev/null +++ b/model-00012-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f408e43081316166202c00c64bf6578d1715ed58546949982d95c104a3d7cdb +size 4865459472 diff --git a/model-00013-of-00063.safetensors b/model-00013-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0852422a7dca5375b492136ce13c1afaf908976 --- /dev/null +++ b/model-00013-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d91a392633437e2f2dd38318a9afac82c33ac3989c6c9c7251de9e3eda3cd1 +size 4596958144 diff --git a/model-00014-of-00063.safetensors b/model-00014-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fcf5cee0813c9e3a9d19d4b0c64fba8008602a0 --- /dev/null +++ b/model-00014-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3008f50eab80547681b524e6619d1e99a9d7938e09ee7e37af3c2572e32aff28 +size 4160947928 diff --git a/model-00015-of-00063.safetensors b/model-00015-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..823269ef81d58f9c8366b0b1ce9d0d99a5a6763d --- /dev/null +++ b/model-00015-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8611f2fec2ec33b28a7d65ac6f46c4cdd6f433743a49acfc81bc7a16460c00 +size 4932568576 diff --git a/model-00016-of-00063.safetensors b/model-00016-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2345bbff6cba1892ae240ae5c5e4cfd0d0027362 --- /dev/null +++ b/model-00016-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e9d8c0744ac39fe21d4124a5ecefec703ddab9ac34073eb6c7d5efb9c5c4b5 +size 4630545568 diff --git a/model-00017-of-00063.safetensors b/model-00017-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d27c3f68a5f9c4ee5ea81c672c024b466ee5b051 --- /dev/null +++ b/model-00017-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002f784d909a0d8169405ff6a293916a030a5e01e6ebba5204441b515c8f2bba +size 4429350616 diff --git a/model-00018-of-00063.safetensors b/model-00018-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3ad4bcb9d61c48501ba659c05418fe9894fc932 --- /dev/null +++ b/model-00018-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce30a9a2a09dfa0c7abb24a3f4c46c1c2e894a6d44824964b44e644a3d6777a9 +size 4597023904 diff --git a/model-00019-of-00063.safetensors b/model-00019-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc07fabcd58d454999551ccf662bbdab8a60aefb --- /dev/null +++ b/model-00019-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8565d8d1f9a80928f7805d625745f4e2a8c0887ec39b41c4f17fe90e1d70f365 +size 4362110000 diff --git a/model-00020-of-00063.safetensors b/model-00020-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63ddaafed8748edf1d0badd1d0378c019f4a4d64 --- /dev/null +++ b/model-00020-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad71584d150f06eba23847a8b00fe546eb33730ce25545c6e0dff63c79afd778 +size 4731340744 diff --git a/model-00021-of-00063.safetensors b/model-00021-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0eb8a4154781bcec10780f7817a75cb5e768351d --- /dev/null +++ b/model-00021-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93710aebb1cd87ae618b9b259f95c9d2dbd725d7df0517e63214f818e2e235e6 +size 4597023904 diff --git a/model-00022-of-00063.safetensors b/model-00022-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1b77170bec991972669f33213230a0ecad31692 --- /dev/null +++ b/model-00022-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a2b32579f6a63a2e40fcc0361716ebd8a91bc615fb2b6db373bef07fe1913e +size 4362110000 diff --git a/model-00023-of-00063.safetensors b/model-00023-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9e0db487eb9f0ec6c2a1aa2761ebbe46d19c8533 --- /dev/null +++ b/model-00023-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec60941791cef306c8414ab200445b582679998c9813384f9634c61681f0304 +size 4731340744 diff --git a/model-00024-of-00063.safetensors b/model-00024-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..67099fa71a60a1465b6be2cf2f0cb40fe8bd757e --- /dev/null +++ b/model-00024-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e627be772032949fb698cf36571f2a87763c3f41c4174ee66048ab3e583065 +size 4597023904 diff --git a/model-00025-of-00063.safetensors b/model-00025-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..958c7edc59eb7f24b6ea65b5fb4e0f31995e85b4 --- /dev/null +++ b/model-00025-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ec6d520bd3b057b951a3495e3ebaa233c8eb3ece6ae9f3e63c4b406c6789dc +size 4362110000 diff --git a/model-00026-of-00063.safetensors b/model-00026-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ce847a81212a34fab2f87182f4c5e1fbb720766 --- /dev/null +++ b/model-00026-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be70adf66a9084d747c83dabd0b6bbf4575ec1212263a2defe42e11b65e3ce7 +size 4731340744 diff --git a/model-00027-of-00063.safetensors b/model-00027-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17e93b35800617538b0c80eb8ac49293c699fef5 --- /dev/null +++ b/model-00027-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce153379080c9c7b6d6297fcb521bc8f4a4dc295add66823f1b763fedd30be6c +size 4596991024 diff --git a/model-00028-of-00063.safetensors b/model-00028-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ff878e36814e982136859d71c070be792dd1d3d --- /dev/null +++ b/model-00028-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:129f7c91a67bc9e1576a37542d487a8801e99465dc8fc7049f59c7ad319b47cb +size 4362175768 diff --git a/model-00029-of-00063.safetensors b/model-00029-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aae25780f9ed292156b7a98ab77dcfd256625de0 --- /dev/null +++ b/model-00029-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe6a8ec8d7f96c6e56caacf780e0d0bbaaec04fd74a11debe002867298cf8dc +size 4697753304 diff --git a/model-00030-of-00063.safetensors b/model-00030-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef564020eb01890594443eac82ad1915cd4faf58 --- /dev/null +++ b/model-00030-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8199817648127a1c1f022cd8395569a15da7ee319e1097b3d4f4fc2e7a16e028 +size 4630578456 diff --git a/model-00031-of-00063.safetensors b/model-00031-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78c9f4d13619ce02bfd5c5f27c957ed9bfe11ab1 --- /dev/null +++ b/model-00031-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b818bacca90846c8e2bc16962d019f8826fb86eea946824588091f4e37d359 +size 4664165888 diff --git a/model-00032-of-00063.safetensors b/model-00032-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13fd455cf7ae426bf57a2504b14012b70074d984 --- /dev/null +++ b/model-00032-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8639047e63970613ea57bcc8cd810148b745f9e66bf16e3eeb99cf57e32450e0 +size 4395730304 diff --git a/model-00033-of-00063.safetensors b/model-00033-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85c213213924d5327604c3158381f7980be12d66 --- /dev/null +++ b/model-00033-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94282365cab6302844aebe7fe177015f7df9337af3a73f85a870011e2bfb52eb +size 4362110000 diff --git a/model-00034-of-00063.safetensors b/model-00034-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d0f0174a31d317c6a53a50473c0f00db3a4c4c9 --- /dev/null +++ b/model-00034-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1df1ff8e54fb4b89e30f151b6ee292e91dc59e4f8e67a2e0820e5e9b3f36b06 +size 4966188896 diff --git a/model-00035-of-00063.safetensors b/model-00035-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0fe29f347726fed56aa386f5756e6a9311357df2 --- /dev/null +++ b/model-00035-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917ef02cca0f0c9b5ca5167768f4d47e1ac0cad0f6af3e1db2c3b416a36f7c47 +size 4362142872 diff --git a/model-00036-of-00063.safetensors b/model-00036-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23816bcaaa8a0e20ecdcf4809280a27b818cf926 --- /dev/null +++ b/model-00036-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afbc6badd5acd7d4fa04cee6d1d41e56feb09f58d6777c013fa2ed56ee667986 +size 4362142888 diff --git a/model-00037-of-00063.safetensors b/model-00037-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6b48c77d303a8d0eb8da275cacf743bc3e0922c --- /dev/null +++ b/model-00037-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dee9e3d6bcd69513b046750793f7284f28b5b2b453bef84de2a3bd3b795e0a9 +size 4966188888 diff --git a/model-00038-of-00063.safetensors b/model-00038-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8574e0552c07a2e990fa6d3e1fd2a4225551d268 --- /dev/null +++ b/model-00038-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a9d742e80c9875b5f8eac333983f5469c0b0a8e1a216864a0601a2554e1a08 +size 4362175752 diff --git a/model-00039-of-00063.safetensors b/model-00039-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8521dc563e1a9d5b5b71d22bb7c0fd8fdf47a1b5 --- /dev/null +++ b/model-00039-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baed720a20e73768355e821e38b166ea2936fe596e7a4a98f872b057d2079861 +size 4362110000 diff --git a/model-00040-of-00063.safetensors b/model-00040-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f7a1d2ecdee68211197f58eaf327b25fbb073c3 --- /dev/null +++ b/model-00040-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcdeee85090706e62b062d0ab021b85406c91ef0a6ac2b95f8b5970689e53060 +size 4966221784 diff --git a/model-00041-of-00063.safetensors b/model-00041-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5d88310e6d63677bd3b2fe1823a86ad1c37d568 --- /dev/null +++ b/model-00041-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d628e22929ed43f0550d2af9d044e0d1f5913eaaaeb6360a935ffd2f0898f781 +size 4362109992 diff --git a/model-00042-of-00063.safetensors b/model-00042-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7d9ff719d146efbf064e35dfddea794ee383049 --- /dev/null +++ b/model-00042-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4c6ceb275738d75ca81908118a2fe6dba85732400488fb3768396e0210999bd +size 4362142888 diff --git a/model-00043-of-00063.safetensors b/model-00043-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..680d1579f65d8a94bfe7fc95dd85de46c5d2de02 --- /dev/null +++ b/model-00043-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3615ce0b1a334da48c5bb2d9543edd1d608d37ca0a738ee21e5a2906a25d1706 +size 4966221784 diff --git a/model-00044-of-00063.safetensors b/model-00044-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cec0db4a387dd68e12e97327f3c641fd32854022 --- /dev/null +++ b/model-00044-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9591d200a47aae21cb6593c083db05ff2b554c66a69475288eb7c3a5e5b3c81 +size 4362109992 diff --git a/model-00045-of-00063.safetensors b/model-00045-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5f4dee1520e6e1c14b9ff61714fd795af7f3555 --- /dev/null +++ b/model-00045-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788ed32a30109487e0e2df4f244308212e93488029c7ce5d7f43d852fd244254 +size 4630578456 diff --git a/model-00046-of-00063.safetensors b/model-00046-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c435ee8dcbece4a86de3d1e49e279287b6cca75 --- /dev/null +++ b/model-00046-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b93290b170406016d5deca73c0f8dd916a347beddd15c14cb5eda84477328f +size 4697786200 diff --git a/model-00047-of-00063.safetensors b/model-00047-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a92a3d1b54d20ea5d3b5ae2d2fe278e756948b95 --- /dev/null +++ b/model-00047-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc085e9712f6efb6509b1b41b8997f64ddb137a9b5b666fc9f67e76e04ecf155 +size 4362109992 diff --git a/model-00048-of-00063.safetensors b/model-00048-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99c02fe6756c8f30ccae91a7b43970b9f137d9b3 --- /dev/null +++ b/model-00048-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa3fd240271b62e2dcc9218b32e9840dbb5606577a728cf7220abb129bfab4c +size 4630611344 diff --git a/model-00049-of-00063.safetensors b/model-00049-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49ea2fdc1e36abc67f8f4273eeaf890a9cf2fdc4 --- /dev/null +++ b/model-00049-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abaeafbc9ebadf0a727918494a100577881c012929233797d75158b9bba740bf +size 4664198776 diff --git a/model-00050-of-00063.safetensors b/model-00050-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce63ebf12e7132f214fffac7d958b44d7b868b22 --- /dev/null +++ b/model-00050-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27093d73f79392faf7437bac1578280672865dd28a68ab2b25c0729df9e6265 +size 4127228968 diff --git a/model-00051-of-00063.safetensors b/model-00051-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..646973bfbc6605386de7fe70cdf09387a19c2cf7 --- /dev/null +++ b/model-00051-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b863528bb04936d6174a956acb7d36fad5a0a4eff2433979a426d9335e86de +size 4899046920 diff --git a/model-00052-of-00063.safetensors b/model-00052-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcee1ad319cf9aab3457cd3f68baf9a4a0f2f42f --- /dev/null +++ b/model-00052-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b713e3da6d6ae15ed5667c1ab1cbce6b857dc50cac4e27cf3b2c915f4e325472 +size 4664198776 diff --git a/model-00053-of-00063.safetensors b/model-00053-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05a5407ee41f2d382de97d8397600dbd6dd89e76 --- /dev/null +++ b/model-00053-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b4d216fc317c34337ab52598338f173796ffb918a747be1881030680e873467 +size 4127196088 diff --git a/model-00054-of-00063.safetensors b/model-00054-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..449d925277c8dda07b5261a239ae054369a44f11 --- /dev/null +++ b/model-00054-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7f7f8c2a317396647c3f15254f02fa7d32ac4e785d9ae0c94ee3df6c6a4bdf +size 4899079792 diff --git a/model-00055-of-00063.safetensors b/model-00055-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e9a94b8d87d6dc184eb662b81dccd4b16308937 --- /dev/null +++ b/model-00055-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24dc4142800ae06ab8cc32152fbeeeefade593ed0776ae201efb9e0ca79a8d09 +size 4697753320 diff --git a/model-00056-of-00063.safetensors b/model-00056-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22b113dd52159de33606d1dad19004a2159ab49e --- /dev/null +++ b/model-00056-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8d94e713634549b809c4a86a1db49e5bdaa6e0a39f3939da7e3c193469a0f9 +size 4362109992 diff --git a/model-00057-of-00063.safetensors b/model-00057-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc3e753295a1b60f1e29f9d3fdd3bd030c87125e --- /dev/null +++ b/model-00057-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9c156d290ce525569b4ed21876959684fd29297bcce12b149a3567e9448634 +size 4630611352 diff --git a/model-00058-of-00063.safetensors b/model-00058-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7b9ec27f12f1444f9aa991d4245694662aafbe3 --- /dev/null +++ b/model-00058-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea35fbf9fea093fdc4cb4cace324f5f9999018f744f0073ff81b499f0031c54 +size 4697753320 diff --git a/model-00059-of-00063.safetensors b/model-00059-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a62901c7ef85ab7556bd9b3226a4a6eeb0b1c719 --- /dev/null +++ b/model-00059-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611492bbec8a9af660ea502ffc43baadaeaf6a6b65e7e8e63c75a56960cf6766 +size 4362077112 diff --git a/model-00060-of-00063.safetensors b/model-00060-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39dfb92c0fbb538483d02d5330e30f0f236b8a29 --- /dev/null +++ b/model-00060-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68715a2558e42ed5faa2c8c20de584ec852ca2f8a8d0c4d1832b9d0fc82f88d0 +size 4630644224 diff --git a/model-00061-of-00063.safetensors b/model-00061-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19a68404c8abbaecd4fb694fdd6fb12213ee6228 --- /dev/null +++ b/model-00061-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69ffe4f339587a6fa63e83eac95083ace294e9bf27f1d9c09f6b75e261f2c37 +size 4697753320 diff --git a/model-00062-of-00063.safetensors b/model-00062-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..43524ecb495e0c6b993235c0e8c87296be8cdf12 --- /dev/null +++ b/model-00062-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a6052751d82122af157027c032c2b3fbc9cc29749d5eb838533a0dea7ee04c +size 4362109984 diff --git a/model-00063-of-00063.safetensors b/model-00063-of-00063.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df59ecd2f8a9f8dc143bbfb34797f4645c713a77 --- /dev/null +++ b/model-00063-of-00063.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e4f4868e01e6107a22091992981315bb1853cf3adf63f524810a4b449c79a9 +size 2483094440 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..f6f858edc7ef60cc250a966f8fee502666e30453 --- /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-00063.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00063.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00063.safetensors", "lm_head.weight": "model-00002-of-00063.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00063.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00063.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00063.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00063.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00063.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00063.safetensors", "model.embed_tokens.weight": "model-00004-of-00063.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00063.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00063.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00063.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00063.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00006-of-00063.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00063.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00063.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00063.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00063.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00063.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00063.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00063.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00063.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00063.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00063.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00063.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00063.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00063.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00008-of-00063.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00063.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00063.safetensors", "model.layers.13.input_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00063.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00063.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00063.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00063.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00063.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00063.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00063.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00063.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00063.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00063.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00063.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00063.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00063.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00063.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00063.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00063.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00063.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00063.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00063.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00063.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00063.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00063.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00063.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00063.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00063.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00063.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00063.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00063.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00063.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00063.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00063.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00063.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00063.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00063.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00063.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00063.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00014-of-00063.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00063.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00014-of-00063.safetensors", "model.layers.20.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00063.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00063.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00063.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00063.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00063.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00063.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00063.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00063.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00063.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00063.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00063.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00016-of-00063.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00063.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.24.input_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00063.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00063.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00063.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00063.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00063.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00063.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00063.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00063.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00063.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00063.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00063.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00019-of-00063.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00063.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00020-of-00063.safetensors", "model.layers.28.input_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00063.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00063.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00020-of-00063.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00063.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00021-of-00063.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.input_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00063.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00063.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00063.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00022-of-00063.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00063.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00022-of-00063.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00063.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00063.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00023-of-00063.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00063.safetensors", "model.layers.31.input_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00063.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00063.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00063.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00063.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00063.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00063.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.input_layernorm.weight": "model-00024-of-00063.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00063.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00063.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00063.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00025-of-00063.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00063.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00063.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00025-of-00063.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00025-of-00063.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00063.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00026-of-00063.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00063.safetensors", "model.layers.35.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.37.input_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00063.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00063.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00026-of-00063.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00027-of-00063.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00063.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00063.safetensors", "model.layers.38.input_layernorm.weight": "model-00027-of-00063.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00063.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00028-of-00063.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00063.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00028-of-00063.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00063.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00028-of-00063.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00063.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00028-of-00063.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00028-of-00063.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00028-of-00063.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00029-of-00063.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.input_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.40.input_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00063.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00029-of-00063.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00063.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00063.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00029-of-00063.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00030-of-00063.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.input_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00063.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00030-of-00063.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00030-of-00063.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00063.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00031-of-00063.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00063.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00031-of-00063.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.input_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00063.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00031-of-00063.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00063.safetensors", "model.layers.42.input_layernorm.weight": "model-00031-of-00063.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00032-of-00063.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00032-of-00063.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.input_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00063.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00032-of-00063.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00032-of-00063.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00063.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00033-of-00063.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00033-of-00063.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00063.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00033-of-00063.safetensors", "model.layers.45.input_layernorm.weight": "model-00033-of-00063.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00033-of-00063.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00034-of-00063.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00034-of-00063.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.input_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00034-of-00063.safetensors", "model.layers.46.input_layernorm.weight": "model-00034-of-00063.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00034-of-00063.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00035-of-00063.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00063.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00035-of-00063.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00035-of-00063.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.input_layernorm.weight": "model-00035-of-00063.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00035-of-00063.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00036-of-00063.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00036-of-00063.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00036-of-00063.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00036-of-00063.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00036-of-00063.safetensors", "model.layers.49.input_layernorm.weight": "model-00036-of-00063.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00036-of-00063.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00037-of-00063.safetensors", "model.layers.5.input_layernorm.weight": "model-00037-of-00063.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00037-of-00063.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00038-of-00063.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00038-of-00063.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00063.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00063.safetensors", "model.layers.51.input_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00038-of-00063.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00038-of-00063.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00038-of-00063.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00039-of-00063.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00039-of-00063.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00039-of-00063.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00039-of-00063.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00039-of-00063.safetensors", "model.layers.52.input_layernorm.weight": "model-00039-of-00063.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00039-of-00063.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00040-of-00063.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00063.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00040-of-00063.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.input_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00040-of-00063.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00040-of-00063.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00041-of-00063.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00041-of-00063.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00041-of-00063.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00041-of-00063.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00063.safetensors", "model.layers.55.input_layernorm.weight": "model-00041-of-00063.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00041-of-00063.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00042-of-00063.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00042-of-00063.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00042-of-00063.safetensors", "model.layers.56.input_layernorm.weight": "model-00042-of-00063.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00043-of-00063.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00043-of-00063.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00063.safetensors", "model.layers.58.input_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00043-of-00063.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00043-of-00063.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00063.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00043-of-00063.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.input_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00043-of-00063.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00043-of-00063.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00044-of-00063.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00063.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00063.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00044-of-00063.safetensors", "model.layers.59.input_layernorm.weight": "model-00044-of-00063.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00045-of-00063.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.input_layernorm.weight": "model-00045-of-00063.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00045-of-00063.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00045-of-00063.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00046-of-00063.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00063.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00046-of-00063.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00046-of-00063.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.input_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.60.input_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00063.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00046-of-00063.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00046-of-00063.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00063.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00047-of-00063.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00063.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00047-of-00063.safetensors", "model.layers.62.input_layernorm.weight": "model-00047-of-00063.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00047-of-00063.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00063.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.input_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00048-of-00063.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00048-of-00063.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00048-of-00063.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00049-of-00063.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00049-of-00063.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.input_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00063.safetensors", "model.layers.64.input_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00063.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00049-of-00063.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00063.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00063.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00050-of-00063.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00050-of-00063.safetensors", "model.layers.66.input_layernorm.weight": "model-00050-of-00063.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00063.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00051-of-00063.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.input_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00051-of-00063.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00051-of-00063.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00051-of-00063.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00052-of-00063.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00052-of-00063.safetensors", "model.layers.69.input_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.input_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00063.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00052-of-00063.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00053-of-00063.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00063.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00063.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00053-of-00063.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.input_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00054-of-00063.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.input_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00063.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00054-of-00063.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00054-of-00063.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00055-of-00063.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.input_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.input_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00063.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00063.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00063.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00056-of-00063.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00063.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00056-of-00063.safetensors", "model.layers.73.input_layernorm.weight": "model-00056-of-00063.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00063.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.input_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00057-of-00063.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00057-of-00063.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00057-of-00063.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00063.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00063.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00058-of-00063.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00058-of-00063.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.76.input_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00058-of-00063.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.input_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00063.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00063.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00063.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00059-of-00063.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00059-of-00063.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00059-of-00063.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00059-of-00063.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00059-of-00063.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.input_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.input_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00060-of-00063.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00060-of-00063.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00060-of-00063.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00060-of-00063.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00061-of-00063.safetensors", "model.layers.8.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00061-of-00063.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00061-of-00063.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.input_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00063.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00063.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00062-of-00063.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00062-of-00063.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00062-of-00063.safetensors", "model.layers.9.input_layernorm.weight": "model-00062-of-00063.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00063-of-00063.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00063-of-00063.safetensors", "model.norm.weight": "model-00063-of-00063.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00063-of-00063.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00063-of-00063.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" +}