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..2a82dc5cce1a4d487a90d0b511b0ff4c41055802 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +base_model: [] +library_name: transformers +tags: +- mergekit +- merge + +--- +# prototype-0.4x258 + +This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). + +## Merge Details +### Merge Method + +This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using /workspace/prototype-0.4x257 as a base. + +### Models Merged + +The following models were included in the merge: +* /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 +* /workspace/cache/models--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d +* /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 +* /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc +* /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb + +### Configuration + +The following YAML configuration was used to produce this model: + +```yaml +models: + - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc + - model: /workspace/cache/models--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 + - model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb +base_model: /workspace/prototype-0.4x257 +select_topk: 0.18 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..0fcec78aaef89ed38b6a242c7405180036efc138 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set loop_messages = messages %} +{% for message in loop_messages %} +{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %} +{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %} +{{ content }} +{% endfor %} +{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fd5aff5b1f4b0e7a5c034ff83d5125dcc3229ab9 --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 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": "4.53.2", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000000000000000000000000000000000000..c17269802dca14d36482e60399ef5334480dd03f --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,15 @@ +models: + - model: /workspace/cache/models--Ppoyaa--MythoNemo-L3.1-70B-v1.0/snapshots/faaa4e992764eb4667b8f541dcf75ce8b7aaadcc + - model: /workspace/cache/models--Sao10K--70B-L3.3-mhnnn-x1/snapshots/3fe1847bbe0dadf7306f3c4bf738f0547676177d + - model: /workspace/cache/models--TheDrummer--Anubis-70B-v1.1/snapshots/47ea1a3368e8d161b09acbc8c211ba4212e4b466 + - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-70B-v1/snapshots/d46ef2629f1c3cd46789a55793c5ff0af60de3e8 + - model: /workspace/cache/models--Sao10K--L3.1-70B-Hanami-x1/snapshots/f054d970fe9119d0237ce97029e6f5b9fce630eb +base_model: /workspace/prototype-0.4x257 +select_topk: 0.18 +merge_method: sce +tokenizer: + source: base +chat_template: llama3 +pad_to_multiple_of: 8 +int8_mask: true +dtype: float32 \ No newline at end of file diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..358a0a37136bd70e014c31854e7f866cb792a0cc --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2b787e1d49b3c32156b12ea1b7f534dafefa2f4525acb0aca448b3012e8941 +size 4395763176 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4efff7b66ba8729e44b39df814c717429830aa0 --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e93ad0ed9245d93163bf6b798958d86632fd6782b6b6b482b2a6f57ddddff4c +size 4697720440 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..25cb5a78ad9e99213184ab3de0cb4c6599c0ae7f --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8341272d7349603c9d25039b9ee56611d80e63ab3c7f86bb29522ec9c29e5f0 +size 4798317608 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ef58362c671a2b5ce1faa949410ad77f57cbeff --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ac55aacb5250854bfb47340f15b1d07f225775ba99664d9036587c81331c3c +size 838894184 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e300e0628d198b0146811525fa4c3834b312787 --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:742f9560920c765108c3b4d6bcec507f32a09b7de9232fc5dda729dd9e2895a6 +size 4202725624 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d8bd92208b763def26426664fe63d5d76cd0b9d --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8627ca7f68303794b776b60eceeb012f82f70f4111cfe28b4c4b486554134cbb +size 4429251984 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6519f479f3cc2043f21d467d7db144e427a14dbb --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d428b14e80d182cdb0858d9c39632f2389f7f3843e063bd61def3af62fa3105a +size 4999676976 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc8fee4cde5839bc5500ee8f8f23322e92a1e6c1 --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbcef43a7cd4cec223c380d8dd9c8f25794ffd602249cb665185ffd326a7ee2 +size 4840260432 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95c7114870e4d4421981e02aefed4cde05c1c996 --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c69c84c93ef01ef5cd5ea3a1fc15ad2225431983e21e6c31d063e9254745828 +size 4328555448 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fbbe6e0cab8b8553a2449f970cc43baa87aac56a --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee5cf500a6a69a8ffc95ac06ee9bce418f1df111bbc9d9eb5135da90a52bde5 +size 4630611344 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0707e167229fcaeaff7896e3f6c79543d57439b0 --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ef41b2fcf43a2af2abe70fbcb664e5438eaf6295e338f36418fb73a5dcbc7d +size 4395763192 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e60d1be5920525354828dea2935aeaf2de48ff41 --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf60f4a0cb8d36f1d2fe6396d87b9d7970522e589a7d23b11cf7574ef1fa4b9c +size 4630512688 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56c4efd2ffc0b1e39d3033ddc2642fc9b7da8a8c --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2291e84755f48a2fa5b212b7f7dfc063523de7be901b5cccbd47ce38515bd58 +size 4664198776 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..255f6db420a36cdf2a7b76dc039e55a9aae3ff7f --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b2ffa3eae71972a2feba99a813824206a5687d695f048ddea98e1a755c232c +size 4395763192 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bfab06f2ae9a2718e29a6d65de0ebcfcab85c3d --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e625aa02b54162e0a1cbe6dce1f593a6f35456ababbe3c76106d23c99b4b3124 +size 4932568576 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..504f6fbd428ccccd3f19f39a0eaa4ed82a19e2b9 --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc876ca9c7f5810fa106e67eac860c7632bb8bc4bfff20a2aad6770353c4251 +size 4597056792 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2c2d04ecafb2caa800e03333c849308e65ffcea --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04549b222fe5b9691aa7811d2bcb0377097ace6f7d59316549bc1f7ff634dc0 +size 4697753320 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42ac66f1c98e89625ce55bea48810d451c6767ec --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8040e7514bba0b7c21380600fedfe50a3db4c85833cf50a39a150bbaea2dd91d +size 4999611208 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ccff77cb17a9083c092435a3415ae13783814b1 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e216bb7dcf87e4201b4e689753da31bff058b75f37771ab1cda76e185ba0e84e +size 4664198768 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e709c6777a080facff5688a705124ec20c20f140 --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39561fffe22cdf60133df7e53359a8cd5aac2e433d26fa1bd600d886c301c27f +size 4966188896 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2eb5894463b7b8fa694a1a4fdea0ce4de480ed52 --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548836ff9936c0740244e9b7ab2da150cfecc6e487bd2f2fc1ab7095f6ce6c37 +size 4664165896 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2fb313c48504b7ecdd4b82b469fb76f1a4eee2e0 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a22ec622fa7b1ec3cd61c94d7ac573cbfd7b26ae8df24ccffec6b196b9b647 +size 4999644088 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c5c35086841dcfd78ff5066be1c3238077dfd2d --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98bfb86f982e4d509d00046f3531c699642c2793da227aff5f724fda7649f9be +size 4966188896 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fb7c42f0327637de9ebc790b79d4cf1fd673af1c --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c253d437d059d01632e6c14a254a25b3f2671747cb5e5bc0cd4d9cfe9c55e73 +size 4697753320 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2522ace04c590d97d37fc26b5f2b74177287ff0 --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af8bcf20795e2c2b1409b3f067e7cebefd1fe36f06be25c9497542825ffcdd8 +size 4865393720 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c853bb5964a6089193f0ae9558205e13a4b1068f --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad33d50ad899f2012173adffe4ce92e84e5ce72bf1b7ae67de5b61852b37d56 +size 4127327624 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e573d655a923977118edc0690a5a3bfc8532e49 --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:362cce533de844683137b46f1fcef6fab1557381c77567aa3cc75f26bf988c9f +size 4697720440 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f56716793d295c408a8d7489b9700333266e39c7 --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12d46ab47da24848fd8118893a008a364a614d6e89f1f8d5b3bae18d944b9587 +size 4899014024 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd9da466431378d699be87d92a02520bbbfb680b --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1daea6038bb7ec3b80fc0a2d36ebcf30da1f8ee1dc44b5811e7e90918cc1d3a +size 4093740184 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7f0df9208400806e13255e29b6f7f0c01899029 --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98d4ac5cbcc9480a19ab2e3bf1b7ca28b5f3df1155b020e1a501eb037a5325d +size 4697753320 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6cb6c8015fe6143d35c6cbc1a70197fadb9b18d3 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297bd9d4cdc9743d6a6dbd818695fcb7eb16beb5dc3d678420d6de860fc09246 +size 4596991032 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c8a6e26e0237be83b47170dc5822bad9ceedb5b --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b130269198d36706b58cb76086ada28d6fff9a553b802ef3f38ac1a31bd15f4e +size 4664165880 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..038ec7f4f2ed3840a0d977f20296bed98475e4a1 --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ba21daad932c797eba99ae45c2d18576a09a4e58f16e8b3db01c595a6b4b64 +size 4395730320 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..abe9928067fe6f23fed5be09d5e1c36037e2dde9 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6a6a59f8e2aaa72821796421eec9c544648935874434bc63a112d79c8d9756 +size 4899014024 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00628cb036c3ebfab902bd6c152d09b07475f2bb --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ad659a63e33521f9386f7bf813feef832d59356d658f9786cbaf7524b4fc27 +size 4127294728 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c30f888fdd0aabd038431d1f5ab8ea44375b11fc --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c8ce14ea3c33684314d802c0362540a87a746c5e43edd3a25af12ed94eb166 +size 4697753320 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20492a9dafd54e0606ee816198f7f5baa961660f --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47d9237210708b54e7e58af9e1bebd90b7736e986e7cc07f689897aac729dd9 +size 4831839168 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ccf8e5866489c5f105e3f5a404a4cff340a8b459 --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174f0fb57d93eb23aca5652b50f318242bccf16e003b49580daba7728efa3505 +size 4160882168 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f007b8acf65677db355b4ad395448434f57bbdb5 --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b06deac98b2d3888175f729d97a11f5e8d0a32e2185793fc190be537d783108 +size 4932634344 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e6079ddca6ccdefcd8aa5885a55f0b27c8558a2 --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c591e8e3a8556c706cc0d37266d0666546a3d1acbb0c54974543232fd592db +size 4362142888 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d93fc663ba5d47d9abdb2a7d3120db438a3ac52d --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f88543fe60e0186927ba8b07f1cf8fdafa351943434c58ab7de8a4bf787b84d +size 4630578456 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..812ab373c8ffc3baa4693966bd915cbf47831a92 --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b9a96335b19c7d130dc05107901189da160598eea9fac15d8341066ec36266 +size 4664165880 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afdff5482345ccfd80e8c955607f7f89740cc199 --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8af5b738a67551a2fe1d3ed388736710eab5e11df2a26f58c8e5649acaf53cd +size 4395730320 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b05963a56bc9738aec86234189b1e94c0b6763bd --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c9ec296987608115efa00b5236c9e9892df4e8703296aeb40be29ac82f7119 +size 4932568576 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76ad0a4767602af4609813d7b33ddb0f3e0f59c5 --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10703933d15b475103de6ff2a7d81ea7a474fa4b84631c5f79e92304f962923 +size 4093740184 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..672432d7e8e3c421b88fb9e1134f8155dfcba8a0 --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c780782d79bc772ff605f36d0ea281bc2c5b0d29c9c45704f8aa242fe16bacd +size 4664165896 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf2d07f91c1fc9378536656912c10cc0a47d7904 --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93c40d062b38d91a05b253591a198edff911c568ec1b1a26c47eb55724aab51 +size 4932568568 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ce11246be01c1a8751ea37f4897632d14babf06e --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9871b7c8df0e9e5545997c206f0b49ddd0c64431cacae34c61570c2de15141d +size 4093740184 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..340c11a04495adb3e8fda34d8fe7041aa72a3f46 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad38e28e58c6e361f5cb624ef2f856d4476f4c4d6d90e233dad051d9925f0b6f +size 4664165896 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..593f223377c4140ed5c3a39dea7f15ec98abab90 --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eb0aa40566b0eb4150577179100d0fdafd8f0317350af9731d98513732e75af +size 4932601448 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58701006c190eb2b5d867d910f939827fc3df0ed --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755d3f83f077af7172a827f4e92c52a17c844bffd518fa499901c452eaf90c7a +size 4999676968 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d25c52c794ad4f670321542f7deed086e8a3c9b2 --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c856658d7bfb54ac998c405e621857fa2f1da4d78302fbe517f518dc78d76a9 +size 4932601464 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56e4210f01a2f53bbc2fc3cf6a8621fa6df59cc3 --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aba9627a5363f03e4915ebd2c6b233517d737213fc32de6aef6b8bfed27febc3 +size 4697753312 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36555ea565fab097561a4eea402c42cd526afa03 --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09fc7089c369bee9cc63db09a5601f52511d4067466024d7dc0e1fae5a02278 +size 4597023904 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76819d7023fe48cca24ad6d1ac1c68d1b685a0ed --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93d20c3853c184b6f57842ba1fd1f03e686f7496e6524150c292dc07eafa97d +size 4395697432 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ede7ca55144c02d472ed3c15ba8507202b3f379 --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a2f16bba0154bb530967ba5060d96a794ff9a3b941c7a94f446798d86d45bb +size 4664198760 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2b92cd3e20f4b1634fbefbf656492b443201f294 --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:889885270af9406c693d8ef41c41bc7fc61ebad33349d08113599f9fe1530aa9 +size 4395697432 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3be185efe35bafa06502c80525eb456fcd33bc25 --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3cf7ef47e9598652a641e0ed6f4e64480f7dc00f6fb9bd035471570b899bd5 +size 4932634344 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c1a8446fd92ff364f22ab64f864ef0eea1aecf7 --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87142fa63b370ef729777c33af6553bad6e2be991bc2de5352ee00d9cda2cd7f +size 4362142880 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff9a7383f7e9923e05a0417ec5e9cde6abc937c9 --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac8860ebad5bc37aa5276247a404a1ce72efe859b5145f1ba1b612e3a3d0bfb +size 4932601432 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5d62646fe21ebd4cc0ffbecf699b952c890e39b8 --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95aa83c44e54c0068ec0fe912a5e9b171e2accd1c4e6230397158caa7d6b6a1c +size 4160816392 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fa55414ff589298a5daafc3ec21156b4ad3ecc80 --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd56581e1109dc7f9c9e62b3f7d6b2be5f9e79efab17614c1299b9503b4be73 +size 3657499680 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..fa2410bd4c43c33cf5186b7165bc70d016aed690 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1 @@ +{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00062.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00062.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00062.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00062.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00062.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00062.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00062.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00062.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00062.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00062.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00062.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00062.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00062.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00062.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00062.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", "lm_head.weight": "model-00005-of-00062.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00062.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00062.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00062.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", "model.embed_tokens.weight": "model-00008-of-00062.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00062.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00062.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00062.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00062.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", "model.layers.2.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00011-of-00062.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00062.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", "model.layers.15.input_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00062.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00062.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00014-of-00062.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.17.input_layernorm.weight": "model-00014-of-00062.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00062.safetensors", "model.layers.25.input_layernorm.weight": "model-00015-of-00062.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.19.input_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00016-of-00062.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00017-of-00062.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00017-of-00062.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.20.input_layernorm.weight": "model-00017-of-00062.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00062.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00018-of-00062.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00018-of-00062.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00019-of-00062.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", "model.layers.22.input_layernorm.weight": "model-00019-of-00062.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00062.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00019-of-00062.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00062.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00020-of-00062.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00020-of-00062.safetensors", "model.layers.24.input_layernorm.weight": "model-00020-of-00062.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00021-of-00062.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00021-of-00062.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.32.input_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00022-of-00062.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00022-of-00062.safetensors", "model.layers.26.input_layernorm.weight": "model-00022-of-00062.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00022-of-00062.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00062.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00062.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00023-of-00062.safetensors", "model.layers.28.input_layernorm.weight": "model-00023-of-00062.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00023-of-00062.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00024-of-00062.safetensors", "model.layers.36.input_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", "model.layers.3.input_layernorm.weight": "model-00024-of-00062.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00025-of-00062.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.38.input_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00026-of-00062.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00026-of-00062.safetensors", "model.layers.31.input_layernorm.weight": "model-00026-of-00062.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00026-of-00062.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00027-of-00062.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00027-of-00062.safetensors", "model.layers.4.input_layernorm.weight": "model-00027-of-00062.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00028-of-00062.safetensors", "model.layers.33.input_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00028-of-00062.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00029-of-00062.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.41.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00029-of-00062.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00029-of-00062.safetensors", "model.layers.35.input_layernorm.weight": "model-00029-of-00062.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00029-of-00062.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00030-of-00062.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00030-of-00062.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.43.input_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", "model.layers.37.input_layernorm.weight": "model-00030-of-00062.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00031-of-00062.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.45.input_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00032-of-00062.safetensors", "model.layers.39.input_layernorm.weight": "model-00032-of-00062.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00032-of-00062.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00032-of-00062.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00033-of-00062.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.47.input_layernorm.weight": "model-00033-of-00062.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00033-of-00062.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00034-of-00062.safetensors", "model.layers.40.input_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00034-of-00062.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00062.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.49.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.42.input_layernorm.weight": "model-00035-of-00062.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00035-of-00062.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00035-of-00062.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00036-of-00062.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.50.input_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00036-of-00062.safetensors", "model.layers.44.input_layernorm.weight": "model-00036-of-00062.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00037-of-00062.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00037-of-00062.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", "model.layers.52.input_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00038-of-00062.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00038-of-00062.safetensors", "model.layers.46.input_layernorm.weight": "model-00038-of-00062.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00038-of-00062.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00039-of-00062.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.input_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00039-of-00062.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.48.input_layernorm.weight": "model-00039-of-00062.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00040-of-00062.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00040-of-00062.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.input_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00041-of-00062.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.5.input_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00041-of-00062.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00042-of-00062.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00042-of-00062.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.input_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", "model.layers.51.input_layernorm.weight": "model-00042-of-00062.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00043-of-00062.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.6.input_layernorm.weight": "model-00043-of-00062.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00043-of-00062.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", "model.layers.53.input_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00045-of-00062.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00045-of-00062.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.61.input_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00045-of-00062.safetensors", "model.layers.55.input_layernorm.weight": "model-00045-of-00062.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00046-of-00062.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00046-of-00062.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00046-of-00062.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.63.input_layernorm.weight": "model-00046-of-00062.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00047-of-00062.safetensors", "model.layers.57.input_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.65.input_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", "model.layers.59.input_layernorm.weight": "model-00048-of-00062.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00049-of-00062.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00049-of-00062.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00049-of-00062.safetensors", "model.layers.67.input_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00050-of-00062.safetensors", "model.layers.60.input_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00050-of-00062.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00050-of-00062.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.69.input_layernorm.weight": "model-00050-of-00062.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00051-of-00062.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00051-of-00062.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", "model.layers.62.input_layernorm.weight": "model-00051-of-00062.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00051-of-00062.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00052-of-00062.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", "model.layers.70.input_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00052-of-00062.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00052-of-00062.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00053-of-00062.safetensors", "model.layers.64.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00053-of-00062.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.72.input_layernorm.weight": "model-00053-of-00062.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00053-of-00062.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00054-of-00062.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00054-of-00062.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00054-of-00062.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", "model.layers.66.input_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00055-of-00062.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.74.input_layernorm.weight": "model-00055-of-00062.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00055-of-00062.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00055-of-00062.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00056-of-00062.safetensors", "model.layers.68.input_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00056-of-00062.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", "model.layers.76.input_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00056-of-00062.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00057-of-00062.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00057-of-00062.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", "model.layers.7.input_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00057-of-00062.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00057-of-00062.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00057-of-00062.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00057-of-00062.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", "model.layers.78.input_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00058-of-00062.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00058-of-00062.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", "model.layers.71.input_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00059-of-00062.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00059-of-00062.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", "model.layers.8.input_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00059-of-00062.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.73.input_layernorm.weight": "model-00060-of-00062.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00060-of-00062.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00060-of-00062.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00060-of-00062.safetensors", "model.norm.weight": "model-00060-of-00062.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00061-of-00062.safetensors", "model.layers.75.input_layernorm.weight": "model-00061-of-00062.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00061-of-00062.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00061-of-00062.safetensors", "model.layers.77.input_layernorm.weight": "model-00061-of-00062.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00062-of-00062.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00062-of-00062.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00062-of-00062.safetensors", "model.layers.79.input_layernorm.weight": "model-00062-of-00062.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00062-of-00062.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00062-of-00062.safetensors", "model.layers.9.input_layernorm.weight": "model-00062-of-00062.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00062-of-00062.safetensors"}} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c68051fe3c4d23234a59316bc52d21f6e3a4182c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}