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..af588f34a58ec04dc4c99f3ddd03c1c81d3130f2 --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +--- +language: +- en +license: llama3 +tags: +- Llama-3.1 +- instruct +- finetune +- reasoning +- hybrid-mode +- chatml +- function calling +- tool use +- json mode +- structured outputs +- atropos +- dataforge +- long context +- roleplaying +- chat +- mlx +base_model: NousResearch/Hermes-4-405B +library_name: transformers +widget: +- example_title: Hermes 4 + messages: + - role: system + content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise, + correct answers. + - role: user + content: Explain the difference between BFS and DFS to a new CS student. +model-index: +- name: Hermes-4-Llama-3.1-405B + results: [] +--- +## 💫 Community Model> Hermes-4-405B by NousResearch + +_👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)_. + +**Model creator**: [NousResearch](https://huggingface.co/NousResearch)
+**Original model**: [Hermes-4-405B](https://huggingface.co/NousResearch/Hermes-4-405B)
+**MLX quantization**: provided by [LM Studio team](https://x.com/lmstudio) using [mlx_lm](https://github.com/ml-explore/mlx-lm)
+ +## Technical Details + +4-bit quantized version of Hermes-4-405B using MLX, optimized for Apple Silicon. + +## Special thanks + +🙏 Special thanks to the [Apple Machine Learning Research](https://github.com/ml-explore) team for creating [MLX](https://github.com/ml-explore/mlx). + +## Disclaimers + +LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio. diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..d894f3b5ebdfe9e094f56e79259fe779156ca47a --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,76 @@ +{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside tags, and then provide your solution or response to the problem.' %} +{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %} +{%- if not thinking is defined %}{% set thinking = false %}{% endif %} +{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %} +{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %} +{%- if tools %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- system_prompt }} + {%- endif %} + {{- "\n\n# Tools\n\nYou are a function calling AI model. You may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": \"\", \"arguments\": }\n<|eot_id|>" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] + '<|eot_id|>' }} + {%- else %} + {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + system_prompt + '<|eot_id|>' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n\n' + message.content + '<|eot_id|>' }} + {%- elif (message.role == "assistant" and not message.tool_calls) %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} + {%- if message.content %} + {%- set content = message['content'] -%} + {%- if thinking %} + {%- if not keep_cots %} + {%- set content = ' ' + content.split('', 1)[1] -%} + {%- endif %} + {%- endif %} + {{- '\n' + content + '<|eot_id|>' }} + {%- endif %} + {%- elif message.role == "assistant" %} + {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }} + {%- if message.content %} + {%- set content = message['content'] -%} + {%- if thinking %} + {%- if not keep_cots %} + {%- set content = ' ' + content.split('', 1)[1] -%} + {%- endif %} + {%- endif %} + {{- '\n' + content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|eot_id|>' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|start_header_id|>user<|end_header_id|>\n' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|eot_id|>' }} + {%- endif %} + {%- endif %} +{%- 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..9f26963b8f52a45b105e2841da9a39fd242b2fa2 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 16384, + "initializer_range": 0.02, + "intermediate_size": 53248, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 128, + "num_hidden_layers": 126, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "quantization": { + "group_size": 64, + "bits": 4 + }, + "quantization_config": { + "group_size": 64, + "bits": 4 + }, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.4", + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..27a9e4c5a8b7c8e0394f0e31149ae19d4822dcd3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.52.4" +} diff --git a/model-00001-of-00044.safetensors b/model-00001-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ddd289048918da16235cf3cc52622e2f42260a6d --- /dev/null +++ b/model-00001-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e721bdb8f7ebc2dbc7f2e0dc9ed5c1d1c91f903cb3d7fa4473c30722b3801101 +size 5089139571 diff --git a/model-00002-of-00044.safetensors b/model-00002-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08396a183e9fd0034a81339cda93d755164fb801 --- /dev/null +++ b/model-00002-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7609bf468f4a5a89aad983cab4af1dadbaa5fb8acfe29bbe0def6d24728d373a +size 5362622015 diff --git a/model-00003-of-00044.safetensors b/model-00003-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86e22bcb1e4583b5d5d7b4d3a322058cab5d8a43 --- /dev/null +++ b/model-00003-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63009354fdc0443a244a7c1a6d85e4eda83d20a3cf45107ef26d10fdeaf55f12 +size 5245181558 diff --git a/model-00004-of-00044.safetensors b/model-00004-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3aa94cda672b0727a1ad009d505c8fc7714df084 --- /dev/null +++ b/model-00004-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef38a8cb9b0dbe61ccd8bb8ce32447b1beea620a75ef757c2cb84a207914726 +size 5360524385 diff --git a/model-00005-of-00044.safetensors b/model-00005-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89601648655a13d50cf5cdef24bad9cb53f5d632 --- /dev/null +++ b/model-00005-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3748888cdc611fb7927d76ca21c0e126b7a73fd4501f275550fdbbda0013391f +size 5362622072 diff --git a/model-00006-of-00044.safetensors b/model-00006-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a99bd073d93011830548fbd80c0d8a8c5db9516 --- /dev/null +++ b/model-00006-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16dd9cf7c3bb1b9fc5c510cc0f52f4b2dfd95e6db8436b6b9a63fb3546a68e94 +size 5245181668 diff --git a/model-00007-of-00044.safetensors b/model-00007-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d803b6402d032722855ffab714862024c2d3be0 --- /dev/null +++ b/model-00007-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40445d11e51d6b084b3ad8903415026fb66cbc64fa78b567a3ff80e0ad291ff0 +size 5352070632 diff --git a/model-00008-of-00044.safetensors b/model-00008-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bcb4d99abbce8cf4610a9af823df14a29267edb2 --- /dev/null +++ b/model-00008-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d41aa4cdf47d9971e82a1d590a4ea7d793b7390a300e43da82456ff0ea2b9d +size 5352136443 diff --git a/model-00009-of-00044.safetensors b/model-00009-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..62e8221c20abdd7e88af4c9954a7625e4576b0b6 --- /dev/null +++ b/model-00009-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2841ccd71b10021ae69bf7c785d150ffa1271d10ad8cf91e8078af004681170d +size 4943191803 diff --git a/model-00010-of-00044.safetensors b/model-00010-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af8729ebd3f2c22f269b3f5f5afa22892249d955 --- /dev/null +++ b/model-00010-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd164446c7710fe2c578bb9358006a2d0a8ed792e2a127f3dbe1dcbbba8ec5d +size 5352136429 diff --git a/model-00011-of-00044.safetensors b/model-00011-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d9c56b39121686982f17fd581e9baabc6173d16 --- /dev/null +++ b/model-00011-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f91f8afbdd475c69befffb61cdcdf636c4c7e935a8fe3285c00ddfc9f22988db +size 5352136441 diff --git a/model-00012-of-00044.safetensors b/model-00012-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5c43377b116be1ebd80b356a4d0e647c188c3178 --- /dev/null +++ b/model-00012-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd22475ff9cbf52ba9064f99dfb947e0770555ddafda6f0932f7b90716dca1a9 +size 4943191775 diff --git a/model-00013-of-00044.safetensors b/model-00013-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7d674f13921dfa2e6634f2621008d7fb2f71f72 --- /dev/null +++ b/model-00013-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4886edd9c6deb0ea631105a4e2b02a9c0dbb371ac85750702ef7992208d63257 +size 5352136423 diff --git a/model-00014-of-00044.safetensors b/model-00014-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78cc0209ccb273faa086dec22f69ff647f4a3c97 --- /dev/null +++ b/model-00014-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d1997996ed20af19fa1e9d8d1dde30eed4889d2dfa6229ce3bc5cc3278966a +size 5352136435 diff --git a/model-00015-of-00044.safetensors b/model-00015-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f664a0182e4722626b996f9c79acf28c0e31fbb --- /dev/null +++ b/model-00015-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3846bf55b2bf0a0aaa9d25f7204bf587380c2e7d97735dec9dcba7f274ac003a +size 4943191775 diff --git a/model-00017-of-00044.safetensors b/model-00017-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d070be2efa837a873719f82a0fcb6a7f2c91ea9f --- /dev/null +++ b/model-00017-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7275e9a7738488f3738b3d423263283c0def43c9e18bd0805d6ea559d98b67a +size 5245181662 diff --git a/model-00018-of-00044.safetensors b/model-00018-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..025bdaa9b4b739461196ba8241183254a8fd3194 --- /dev/null +++ b/model-00018-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbb20cbe4d9502008f10da73209537e1f1764da21e4d5e6721de215f8e02018 +size 5360524430 diff --git a/model-00019-of-00044.safetensors b/model-00019-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ea3f5a7a2ef2e18aa0056489cf5fb34a5c7e263 --- /dev/null +++ b/model-00019-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d91f7a6dafd0da777925ebb2a70da5c21b5e4d68ef38668f8c92adcc008109 +size 5362622058 diff --git a/model-00020-of-00044.safetensors b/model-00020-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ead3da8cefdd7e408d6a7cd3443b61557e5211b1 --- /dev/null +++ b/model-00020-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec05c3427caed8294348367ccd3f493ba3663276790a95268787a0466a0153f +size 5245181650 diff --git a/model-00021-of-00044.safetensors b/model-00021-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4bb5c4410d0013e0dbc5835120439fe2875cab07 --- /dev/null +++ b/model-00021-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d5daef22abe2471d4b06286934caaa30e6f0d5fa657a009c924ddfa66cc357b +size 5352070664 diff --git a/model-00022-of-00044.safetensors b/model-00022-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32a37bde55ef5f10e268040cf02e30367b0cdef1 --- /dev/null +++ b/model-00022-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e518440b88c904557ebdde29a06819a1974d605f1dcbac2877ec414628c810 +size 5352136435 diff --git a/model-00023-of-00044.safetensors b/model-00023-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17e6d398b5d2a6ec74252a3b7772585c5b1ad889 --- /dev/null +++ b/model-00023-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0270b4e5313a56389326f6f41071820cfe5da705ae0716833b5dfac102a8493d +size 4943191805 diff --git a/model-00024-of-00044.safetensors b/model-00024-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5ea0d0bcb5dd84460babcdde0634e94227205340 --- /dev/null +++ b/model-00024-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51e20182e617d789b14b8e872a5ac60229bdb7612d119f7e11511d9dea44dbf +size 5352136409 diff --git a/model-00025-of-00044.safetensors b/model-00025-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..779a0d6421f1ae06ef102db448815c3e559a9952 --- /dev/null +++ b/model-00025-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0011f8b239452731617cbe5ac38b4dfc1fe7cd22bfafc45ed5271189cf0bbcbe +size 5352136441 diff --git a/model-00026-of-00044.safetensors b/model-00026-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e585158260404b1b09b09bf9be7c00a44b42163f --- /dev/null +++ b/model-00026-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d250dc755dc02c18160022cbe9501ed8ff00ef2c3e06c4a4a9a728820d53c2 +size 4943191781 diff --git a/model-00027-of-00044.safetensors b/model-00027-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f7c4a240ed661f57c25b59ee31567c0a98a11f2f --- /dev/null +++ b/model-00027-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:831263af99971de82adb30b9a9913ab75ae3864a462aafd4d526bfa2d6707597 +size 5352136433 diff --git a/model-00028-of-00044.safetensors b/model-00028-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c73410ab35c8fbbb7d7659ddf0d61dc166023e3e --- /dev/null +++ b/model-00028-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37b3baf109d13bc6e09c1b07a97861ba68cd7fc3359426e715349a0b8beff74c +size 5352136415 diff --git a/model-00029-of-00044.safetensors b/model-00029-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..00851a1cea69e11486b80ae7386ca18ab89c628b --- /dev/null +++ b/model-00029-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f632e0f28d48a153b78d89ee38486a3d7603b8ec7dd6c82ca934e0081d6da11c +size 4943191767 diff --git a/model-00030-of-00044.safetensors b/model-00030-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9b8f24849412a3db8aa8cc51850ba3a751acaa7 --- /dev/null +++ b/model-00030-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57d7ef433c3be68cea0a58dcbe76fb133a82452de1ec1d36ff71201bb0a62ff +size 5362622048 diff --git a/model-00031-of-00044.safetensors b/model-00031-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afbb7d996fa04f309dbbd84fc17500f79cc889e4 --- /dev/null +++ b/model-00031-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e1b90b031bef792b787a72830d85f06c903ad05c6f8201c2d4ef27c1f3dfdf3 +size 5245181630 diff --git a/model-00032-of-00044.safetensors b/model-00032-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4a178bd6e80dc916ba9d4104662debbc0fe3c77 --- /dev/null +++ b/model-00032-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca17d1eced5b96bf9484f6c588e627707ebec6b01b1d5f426557cdfaf61dc7e8 +size 5360524430 diff --git a/model-00034-of-00044.safetensors b/model-00034-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d918f388b07690be1873063c87193d8fd56b2164 --- /dev/null +++ b/model-00034-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec0fe5be2a4b8940d3b0bbfe8b1e791b2074a53c2268cb504036f9916428908 +size 5245181672 diff --git a/model-00035-of-00044.safetensors b/model-00035-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d3da7f79bdf0131bed4ac4a000846619fe3005a --- /dev/null +++ b/model-00035-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa508ed3f87aab2a22d5d831c22ddba6acc8ceab73d346a7765fdeb2f92bfeec +size 5352070711 diff --git a/model-00036-of-00044.safetensors b/model-00036-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fcb1479541499d7a2c199b74c6e8fe5200b2cb4d --- /dev/null +++ b/model-00036-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94370ad174054706cb6c60da509a5aa70b4993bba3db942ea6b5aaeae527c258 +size 5352136509 diff --git a/model-00037-of-00044.safetensors b/model-00037-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..447502ee721715c569927a7daf6279cb26b29cff --- /dev/null +++ b/model-00037-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7ab5a62ad127311b972fdeace491ef4416b764cacc7feeae3e8d92af824c06 +size 4943191845 diff --git a/model-00038-of-00044.safetensors b/model-00038-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2700712544b813c9ed327e21787cf311fba8dd2a --- /dev/null +++ b/model-00038-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e99e91749d6074104411e3fe51253544d8a08066cbb81977752ed66dc37039 +size 5352136509 diff --git a/model-00039-of-00044.safetensors b/model-00039-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1fc0fc44c24e580148577c4db9f4134ade60bc7 --- /dev/null +++ b/model-00039-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77df95592a9c256a849dbea5dc8eb5ee1e924f6998269a38f5a3369f370b05e3 +size 5352136493 diff --git a/model-00040-of-00044.safetensors b/model-00040-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7ee9885f8edba1dce0188549fadbbb6fb970e1d --- /dev/null +++ b/model-00040-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc27f2843cea872c6e0fbf355ea8fd73d6c782a6663a63486d02eb9982c68243 +size 4943191863 diff --git a/model-00041-of-00044.safetensors b/model-00041-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05129cd692a0b0479984ce1ee2c1fb8450c53345 --- /dev/null +++ b/model-00041-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5e82bf059f1fff2aaf02cec59df5c228fa4a0fa31cfebd9c3f2cac9a1cce26 +size 5352136487 diff --git a/model-00042-of-00044.safetensors b/model-00042-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f36cf9de9b9c69a5347eefdf029722c88add452c --- /dev/null +++ b/model-00042-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfb3dc3b2f9350a648f7a27929ab39b368eb94c3aec557bd9030e1af56472ef +size 5352136479 diff --git a/model-00043-of-00044.safetensors b/model-00043-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9994c1e0e5adb28eb153fb3d9325a7dbb79c376 --- /dev/null +++ b/model-00043-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c334662c36bd94def7df7bed9318ead3c23d77f72df5594eecd6eeda82f374 +size 4943191839 diff --git a/model-00044-of-00044.safetensors b/model-00044-of-00044.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92ef9c6da0c5f5679b5e63514bb89fa57a2a72a8 --- /dev/null +++ b/model-00044-of-00044.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43e6ccd3e28ae16b2ddb231d37453afdd7d73283334097f26d8f93fbe6097cd +size 2654307977 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ff0cbe034fe8269e18080a947cb29ca8f2b697bb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2913 @@ +{ + "metadata": { + "total_size": 228298489856, + "total_parameters": 405853388800 + }, + "weight_map": { + "lm_head.biases": "model-00044-of-00044.safetensors", + "lm_head.scales": "model-00044-of-00044.safetensors", + "lm_head.weight": "model-00044-of-00044.safetensors", + "model.embed_tokens.biases": "model-00001-of-00044.safetensors", + "model.embed_tokens.scales": "model-00001-of-00044.safetensors", + "model.embed_tokens.weight": "model-00001-of-00044.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.down_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.gate_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.up_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.100.input_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.down_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.down_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.down_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.gate_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.gate_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.up_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.up_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.mlp.up_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.k_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.k_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.o_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.o_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.q_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.q_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.v_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.v_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.100.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.input_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.101.mlp.down_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.down_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.down_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.gate_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.gate_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.up_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.101.mlp.up_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.mlp.up_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.101.self_attn.k_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.k_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.o_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.o_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.q_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.q_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.v_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.v_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.101.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.102.input_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.down_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.down_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.down_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.gate_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.gate_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.up_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.up_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.mlp.up_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.k_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.k_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.o_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.o_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.q_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.q_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.v_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.v_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.102.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.input_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.down_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.down_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.down_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.gate_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.gate_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.up_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.up_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.mlp.up_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.post_attention_layernorm.weight": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.k_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.k_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.o_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.o_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.q_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.q_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.v_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.v_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.103.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.input_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.104.mlp.down_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.down_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.down_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.gate_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.gate_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.gate_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.mlp.up_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.104.mlp.up_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.104.mlp.up_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.104.self_attn.k_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.k_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.k_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.o_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.o_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.o_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.q_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.q_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.q_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.v_proj.biases": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.v_proj.scales": "model-00036-of-00044.safetensors", + "model.layers.104.self_attn.v_proj.weight": "model-00036-of-00044.safetensors", + "model.layers.105.input_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.down_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.down_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.down_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.gate_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.gate_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.up_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.up_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.mlp.up_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.k_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.k_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.o_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.o_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.q_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.q_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.v_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.v_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.105.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.input_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.down_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.down_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.down_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.gate_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.gate_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.up_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.up_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.mlp.up_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.post_attention_layernorm.weight": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.k_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.k_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.o_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.o_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.q_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.q_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.v_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.v_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.106.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.input_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.107.mlp.down_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.down_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.down_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.gate_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.gate_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.gate_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.mlp.up_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.107.mlp.up_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.107.mlp.up_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.107.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.107.self_attn.k_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.k_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.k_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.o_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.o_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.o_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.q_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.q_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.q_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.v_proj.biases": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.v_proj.scales": "model-00037-of-00044.safetensors", + "model.layers.107.self_attn.v_proj.weight": "model-00037-of-00044.safetensors", + "model.layers.108.input_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.down_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.down_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.down_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.gate_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.gate_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.up_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.up_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.mlp.up_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.k_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.k_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.o_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.o_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.q_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.q_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.v_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.v_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.108.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.input_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.down_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.down_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.down_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.gate_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.gate_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.up_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.up_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.mlp.up_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.post_attention_layernorm.weight": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.k_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.k_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.o_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.o_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.q_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.q_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.v_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.v_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.109.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.11.input_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.down_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.gate_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.up_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.110.input_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.110.mlp.down_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.110.mlp.down_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.mlp.down_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.110.mlp.gate_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.110.mlp.gate_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.mlp.gate_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.110.mlp.up_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.110.mlp.up_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.110.mlp.up_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.110.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.110.self_attn.k_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.k_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.k_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.o_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.o_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.o_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.q_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.q_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.q_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.v_proj.biases": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.v_proj.scales": "model-00038-of-00044.safetensors", + "model.layers.110.self_attn.v_proj.weight": "model-00038-of-00044.safetensors", + "model.layers.111.input_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.down_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.down_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.down_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.gate_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.gate_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.up_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.up_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.mlp.up_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.k_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.k_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.o_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.o_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.q_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.q_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.v_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.v_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.111.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.input_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.down_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.down_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.down_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.gate_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.gate_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.up_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.up_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.mlp.up_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.post_attention_layernorm.weight": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.k_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.k_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.o_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.o_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.q_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.q_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.v_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.v_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.112.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.input_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.113.mlp.down_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.113.mlp.down_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.113.mlp.down_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.mlp.gate_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.113.mlp.gate_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.113.mlp.gate_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.mlp.up_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.113.mlp.up_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.113.mlp.up_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.113.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.113.self_attn.k_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.k_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.k_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.o_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.o_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.o_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.q_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.q_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.q_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.v_proj.biases": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.v_proj.scales": "model-00039-of-00044.safetensors", + "model.layers.113.self_attn.v_proj.weight": "model-00039-of-00044.safetensors", + "model.layers.114.input_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.down_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.down_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.down_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.gate_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.gate_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.up_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.up_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.mlp.up_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.k_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.k_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.o_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.o_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.q_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.q_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.v_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.v_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.114.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.input_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.down_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.down_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.down_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.gate_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.gate_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.up_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.up_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.mlp.up_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.post_attention_layernorm.weight": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.k_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.k_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.o_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.o_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.q_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.q_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.v_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.v_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.115.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.116.input_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.down_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.down_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.down_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.gate_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.116.mlp.gate_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.116.mlp.gate_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.116.mlp.up_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.up_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.116.mlp.up_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.116.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.116.self_attn.k_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.k_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.k_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.o_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.o_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.o_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.q_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.q_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.q_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.v_proj.biases": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.v_proj.scales": "model-00040-of-00044.safetensors", + "model.layers.116.self_attn.v_proj.weight": "model-00040-of-00044.safetensors", + "model.layers.117.input_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.down_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.down_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.down_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.gate_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.gate_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.up_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.up_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.mlp.up_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.k_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.k_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.o_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.o_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.q_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.q_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.v_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.v_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.117.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.input_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.down_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.down_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.down_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.gate_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.gate_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.up_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.up_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.mlp.up_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.post_attention_layernorm.weight": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.k_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.k_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.o_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.o_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.q_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.q_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.v_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.v_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.118.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.119.input_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.down_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.down_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.down_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.gate_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.gate_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.119.mlp.gate_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.119.mlp.up_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.up_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.119.mlp.up_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.119.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.119.self_attn.k_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.k_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.k_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.o_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.o_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.o_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.q_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.q_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.q_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.v_proj.biases": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.v_proj.scales": "model-00041-of-00044.safetensors", + "model.layers.119.self_attn.v_proj.weight": "model-00041-of-00044.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.down_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.gate_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.up_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.120.input_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.down_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.down_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.down_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.gate_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.gate_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.up_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.up_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.mlp.up_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.k_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.k_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.o_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.o_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.q_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.q_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.v_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.v_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.120.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.input_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.down_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.down_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.down_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.gate_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.gate_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.up_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.up_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.mlp.up_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.post_attention_layernorm.weight": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.k_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.k_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.o_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.o_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.q_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.q_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.v_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.v_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.121.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.122.input_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.down_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.down_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.down_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.gate_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.gate_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.gate_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.122.mlp.up_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.up_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.122.mlp.up_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.122.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.122.self_attn.k_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.k_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.k_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.o_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.o_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.o_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.q_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.q_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.q_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.v_proj.biases": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.v_proj.scales": "model-00042-of-00044.safetensors", + "model.layers.122.self_attn.v_proj.weight": "model-00042-of-00044.safetensors", + "model.layers.123.input_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.down_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.down_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.down_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.gate_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.gate_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.up_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.up_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.mlp.up_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.k_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.k_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.o_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.o_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.q_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.q_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.v_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.v_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.123.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.input_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.down_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.down_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.down_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.gate_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.gate_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.gate_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.up_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.up_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.mlp.up_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.post_attention_layernorm.weight": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.k_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.k_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.o_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.o_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.q_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.q_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.v_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.v_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.124.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.125.input_layernorm.weight": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.down_proj.biases": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.down_proj.scales": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.down_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.gate_proj.biases": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.gate_proj.scales": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.gate_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.up_proj.biases": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.up_proj.scales": "model-00044-of-00044.safetensors", + "model.layers.125.mlp.up_proj.weight": "model-00044-of-00044.safetensors", + "model.layers.125.post_attention_layernorm.weight": "model-00044-of-00044.safetensors", + "model.layers.125.self_attn.k_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.k_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.k_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.o_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.o_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.o_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.q_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.q_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.q_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.v_proj.biases": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.v_proj.scales": "model-00043-of-00044.safetensors", + "model.layers.125.self_attn.v_proj.weight": "model-00043-of-00044.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.down_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.gate_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.up_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00005-of-00044.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.14.input_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.down_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.gate_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.up_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00044.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.input_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.down_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.gate_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.up_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.input_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.down_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.gate_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.up_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00006-of-00044.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00044.safetensors", + "model.layers.17.input_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.down_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.gate_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.up_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.input_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.down_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.gate_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.up_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.input_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.19.mlp.down_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.gate_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.up_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00007-of-00044.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00044.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00044.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00044.safetensors", + "model.layers.20.input_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.down_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.gate_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.up_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.input_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.down_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.gate_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.up_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.input_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.22.mlp.down_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.gate_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.mlp.up_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00008-of-00044.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00044.safetensors", + "model.layers.23.input_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.down_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.gate_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.up_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.input_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.down_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.gate_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.up_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.input_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.25.mlp.down_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.gate_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.mlp.up_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00009-of-00044.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00044.safetensors", + "model.layers.26.input_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.down_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.gate_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.up_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.input_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.down_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.gate_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.up_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.input_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.28.mlp.down_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.mlp.gate_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.mlp.up_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00010-of-00044.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00044.safetensors", + "model.layers.29.input_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.down_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.gate_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.up_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.down_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.gate_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.up_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.30.input_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.down_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.gate_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.up_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.input_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.31.mlp.down_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.mlp.gate_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.mlp.up_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00011-of-00044.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00044.safetensors", + "model.layers.32.input_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.down_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.gate_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.up_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.input_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.down_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.gate_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.up_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.34.input_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.down_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.gate_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.34.mlp.up_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00012-of-00044.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00044.safetensors", + "model.layers.35.input_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.down_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.gate_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.up_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.input_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.down_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.gate_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.up_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.37.input_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.down_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.gate_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.37.mlp.up_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00013-of-00044.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00044.safetensors", + "model.layers.38.input_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.down_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.gate_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.up_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.input_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.down_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.gate_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.up_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.down_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.gate_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.up_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.40.input_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.down_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.gate_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.40.mlp.up_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00014-of-00044.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00044.safetensors", + "model.layers.41.input_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.down_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.gate_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.up_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.input_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.down_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.gate_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.up_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.43.input_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.down_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.gate_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.up_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00015-of-00044.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00044.safetensors", + "model.layers.44.input_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.down_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.gate_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.up_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.input_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.down_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.gate_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.up_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.46.input_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.down_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.gate_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.up_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00016-of-00044.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00044.safetensors", + "model.layers.47.input_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.down_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.gate_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.up_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.input_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.down_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.down_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.gate_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.gate_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.up_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.up_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.k_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.o_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.q_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.v_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.49.input_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.down_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.down_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.gate_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.gate_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.up_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.up_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.49.self_attn.k_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.o_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.49.self_attn.q_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.v_proj.biases": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00017-of-00044.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00044.safetensors", + "model.layers.5.input_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.down_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.gate_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.up_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00044.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00044.safetensors", + "model.layers.50.input_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.down_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.down_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.gate_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.gate_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.up_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.up_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.k_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.o_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.q_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.v_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.input_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.down_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.down_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.gate_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.gate_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.up_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.up_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.k_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.o_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.q_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.v_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.52.input_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.down_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.down_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.gate_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.gate_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.up_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.up_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.k_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.o_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.q_proj.biases": "model-00018-of-00044.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00018-of-00044.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00044.safetensors", + "model.layers.52.self_attn.v_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.input_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.down_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.down_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.gate_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.gate_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.up_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.up_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.k_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.o_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.q_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.v_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.input_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.down_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.down_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.gate_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.gate_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.up_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.up_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.k_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.o_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.q_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.v_proj.biases": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00019-of-00044.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.55.input_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.down_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.down_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.gate_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.gate_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.up_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.up_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.k_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.o_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.q_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00044.safetensors", + "model.layers.55.self_attn.v_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.input_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.down_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.down_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.gate_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.gate_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.up_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.up_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.k_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.o_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.q_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.v_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.input_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.down_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.down_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.gate_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.gate_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.up_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.up_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.k_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.o_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.q_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.v_proj.biases": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00020-of-00044.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00044.safetensors", + "model.layers.58.input_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.down_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.down_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.gate_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.gate_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.up_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.up_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.k_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.o_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.q_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.v_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.input_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.down_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.down_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.gate_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.gate_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.up_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.up_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.k_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.o_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.q_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.v_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.down_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.gate_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.up_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.60.input_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.60.mlp.down_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.down_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.gate_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.gate_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.up_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.60.mlp.up_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.60.self_attn.k_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.o_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.q_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.v_proj.biases": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00021-of-00044.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00044.safetensors", + "model.layers.61.input_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.down_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.down_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.gate_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.gate_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.up_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.up_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.k_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.o_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.q_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.v_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.input_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.down_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.down_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.gate_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.gate_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.up_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.up_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.k_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.o_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.q_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.v_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.input_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.63.mlp.down_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.down_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.gate_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.gate_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.mlp.up_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.63.mlp.up_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.63.self_attn.k_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.o_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.q_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.v_proj.biases": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00022-of-00044.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00044.safetensors", + "model.layers.64.input_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.down_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.down_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.gate_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.gate_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.up_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.up_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.k_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.k_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.o_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.o_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.q_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.q_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.v_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.v_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.input_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.down_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.down_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.gate_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.gate_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.up_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.up_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.k_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.k_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.o_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.o_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.q_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.q_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.v_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.v_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.input_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.66.mlp.down_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.down_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.gate_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.gate_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.mlp.up_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.66.mlp.up_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.66.self_attn.k_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.k_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.o_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.o_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.q_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.q_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.v_proj.biases": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.v_proj.scales": "model-00023-of-00044.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00023-of-00044.safetensors", + "model.layers.67.input_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.down_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.down_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.gate_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.gate_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.up_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.up_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.k_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.k_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.o_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.o_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.q_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.q_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.v_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.v_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.input_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.down_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.down_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.gate_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.gate_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.up_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.up_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.k_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.k_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.o_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.o_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.q_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.q_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.v_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.v_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.input_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.69.mlp.down_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.69.mlp.down_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.mlp.gate_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.69.mlp.gate_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.mlp.up_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.69.mlp.up_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.69.self_attn.k_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.k_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.o_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.o_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.q_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.q_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.v_proj.biases": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.v_proj.scales": "model-00024-of-00044.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00044.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.down_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.gate_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.up_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.70.input_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.down_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.down_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.gate_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.gate_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.up_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.up_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.k_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.k_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.o_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.o_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.q_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.q_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.v_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.v_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.input_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.down_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.down_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.gate_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.gate_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.up_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.up_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.k_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.k_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.o_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.o_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.q_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.q_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.v_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.v_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.input_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.72.mlp.down_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.72.mlp.down_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.mlp.gate_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.72.mlp.gate_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.mlp.up_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.72.mlp.up_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.72.self_attn.k_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.k_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.o_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.o_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.q_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.q_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.v_proj.biases": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.v_proj.scales": "model-00025-of-00044.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00025-of-00044.safetensors", + "model.layers.73.input_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.down_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.down_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.gate_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.gate_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.up_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.up_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.k_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.k_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.o_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.o_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.q_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.q_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.v_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.v_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.input_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.down_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.down_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.gate_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.gate_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.up_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.up_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.k_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.k_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.o_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.o_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.q_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.q_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.v_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.v_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.75.input_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.down_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.down_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.gate_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.75.mlp.gate_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.75.mlp.up_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.up_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.75.self_attn.k_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.k_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.o_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.o_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.q_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.q_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.v_proj.biases": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.v_proj.scales": "model-00026-of-00044.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00026-of-00044.safetensors", + "model.layers.76.input_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.down_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.down_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.gate_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.gate_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.up_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.up_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.k_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.k_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.o_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.o_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.q_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.q_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.v_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.v_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.input_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.down_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.down_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.gate_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.gate_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.up_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.up_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.k_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.k_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.o_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.o_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.q_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.q_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.v_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.v_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.78.input_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.down_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.down_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.gate_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.gate_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.78.mlp.up_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.up_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.78.self_attn.k_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.k_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.o_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.o_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.q_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.q_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.v_proj.biases": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.v_proj.scales": "model-00027-of-00044.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00027-of-00044.safetensors", + "model.layers.79.input_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.down_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.down_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.gate_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.gate_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.up_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.up_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.k_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.k_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.o_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.o_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.q_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.q_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.v_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.v_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.8.input_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.down_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.gate_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.up_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00003-of-00044.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00044.safetensors", + "model.layers.80.input_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.down_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.down_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.down_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.gate_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.gate_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.up_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.up_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.mlp.up_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.post_attention_layernorm.weight": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.k_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.k_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.o_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.o_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.q_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.q_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.v_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.v_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.80.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.81.input_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.down_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.down_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.down_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.gate_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.gate_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.gate_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.81.mlp.up_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.up_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.81.mlp.up_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.81.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.81.self_attn.k_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.k_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.k_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.o_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.o_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.o_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.q_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.q_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.q_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.v_proj.biases": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.v_proj.scales": "model-00028-of-00044.safetensors", + "model.layers.81.self_attn.v_proj.weight": "model-00028-of-00044.safetensors", + "model.layers.82.input_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.down_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.down_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.down_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.gate_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.gate_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.up_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.up_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.mlp.up_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.k_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.k_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.o_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.o_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.q_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.q_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.v_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.v_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.82.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.input_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.down_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.down_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.down_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.gate_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.gate_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.gate_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.up_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.up_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.mlp.up_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.post_attention_layernorm.weight": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.k_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.k_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.o_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.o_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.q_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.q_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.v_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.v_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.83.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.84.input_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.down_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.down_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.down_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.gate_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.gate_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.up_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.up_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.84.mlp.up_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.84.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.84.self_attn.k_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.k_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.k_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.o_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.o_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.o_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.q_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.q_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.q_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.v_proj.biases": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.v_proj.scales": "model-00029-of-00044.safetensors", + "model.layers.84.self_attn.v_proj.weight": "model-00029-of-00044.safetensors", + "model.layers.85.input_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.down_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.down_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.down_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.gate_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.gate_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.up_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.up_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.mlp.up_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.k_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.k_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.o_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.o_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.q_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.q_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.v_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.v_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.85.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.input_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.down_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.down_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.down_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.gate_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.gate_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.gate_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.up_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.up_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.mlp.up_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.post_attention_layernorm.weight": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.k_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.k_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.o_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.o_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.q_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.q_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.v_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.v_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.86.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.87.input_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.down_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.down_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.down_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.gate_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.gate_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.up_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.up_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.87.mlp.up_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.87.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.87.self_attn.k_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.k_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.k_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.o_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.87.self_attn.o_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.87.self_attn.o_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.q_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.q_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.q_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.v_proj.biases": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.v_proj.scales": "model-00030-of-00044.safetensors", + "model.layers.87.self_attn.v_proj.weight": "model-00030-of-00044.safetensors", + "model.layers.88.input_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.down_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.down_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.down_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.gate_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.gate_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.up_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.up_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.mlp.up_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.k_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.k_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.o_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.o_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.q_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.q_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.v_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.v_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.88.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.input_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.down_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.down_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.down_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.gate_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.gate_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.gate_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.up_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.up_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.mlp.up_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.post_attention_layernorm.weight": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.k_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.k_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.o_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.o_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.o_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.q_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.q_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.v_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.v_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.89.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.down_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.gate_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.up_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00004-of-00044.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00044.safetensors", + "model.layers.90.input_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.down_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.down_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.down_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.gate_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.gate_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.up_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.up_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.90.mlp.up_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.90.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.90.self_attn.k_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.k_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.k_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.o_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.90.self_attn.o_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.90.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.90.self_attn.q_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.q_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.q_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.v_proj.biases": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.v_proj.scales": "model-00031-of-00044.safetensors", + "model.layers.90.self_attn.v_proj.weight": "model-00031-of-00044.safetensors", + "model.layers.91.input_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.down_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.down_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.down_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.gate_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.gate_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.up_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.up_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.mlp.up_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.k_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.k_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.o_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.o_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.q_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.q_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.v_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.v_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.91.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.input_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.down_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.down_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.down_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.gate_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.gate_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.gate_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.up_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.up_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.mlp.up_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.post_attention_layernorm.weight": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.k_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.k_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.k_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.o_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.o_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.o_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.q_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.q_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.v_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.v_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.92.self_attn.v_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.93.input_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.down_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.down_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.down_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.gate_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.gate_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.up_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.up_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.mlp.up_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.93.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.k_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.k_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.o_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.o_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.q_proj.biases": "model-00032-of-00044.safetensors", + "model.layers.93.self_attn.q_proj.scales": "model-00032-of-00044.safetensors", + "model.layers.93.self_attn.q_proj.weight": "model-00032-of-00044.safetensors", + "model.layers.93.self_attn.v_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.v_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.93.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.input_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.down_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.down_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.down_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.gate_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.gate_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.up_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.up_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.mlp.up_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.k_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.k_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.o_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.o_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.q_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.q_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.v_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.v_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.94.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.input_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.down_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.down_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.down_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.gate_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.gate_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.gate_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.up_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.up_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.mlp.up_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.post_attention_layernorm.weight": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.k_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.k_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.k_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.o_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.o_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.o_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.q_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.q_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.v_proj.biases": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.v_proj.scales": "model-00033-of-00044.safetensors", + "model.layers.95.self_attn.v_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.96.input_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.down_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.down_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.down_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.gate_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.gate_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.up_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.up_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.mlp.up_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.96.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.k_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.k_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.o_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.o_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.q_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.q_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.q_proj.weight": "model-00033-of-00044.safetensors", + "model.layers.96.self_attn.v_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.v_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.96.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.input_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.down_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.down_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.down_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.gate_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.gate_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.up_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.up_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.mlp.up_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.k_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.k_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.o_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.o_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.q_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.q_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.v_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.v_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.97.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.input_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.down_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.down_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.down_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.gate_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.gate_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.gate_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.up_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.up_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.mlp.up_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.post_attention_layernorm.weight": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.k_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.k_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.k_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.o_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.o_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.o_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.q_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.q_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.q_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.v_proj.biases": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.v_proj.scales": "model-00034-of-00044.safetensors", + "model.layers.98.self_attn.v_proj.weight": "model-00034-of-00044.safetensors", + "model.layers.99.input_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.down_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.down_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.down_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.gate_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.gate_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.gate_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.up_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.up_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.mlp.up_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.post_attention_layernorm.weight": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.k_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.k_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.k_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.o_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.o_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.o_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.q_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.q_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.q_proj.weight": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.v_proj.biases": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.v_proj.scales": "model-00035-of-00044.safetensors", + "model.layers.99.self_attn.v_proj.weight": "model-00035-of-00044.safetensors", + "model.norm.weight": "model-00044-of-00044.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..278b7f0f84be865c4687700ee7b3c63d89a51e18 --- /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": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..37d7807e935d1462a2f093828ac5ee9a08c628a7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e4573a56ca97b0233ddc2dd63f634aeee35b84f352d2ce2aaa5992735cfcad +size 17209827 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1916c2b20aa070a9deb86df289cd924027e7ac85 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "add_bos_token": true, + "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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128003": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "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": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "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": "<|end_of_text|>", + "tokenizer_class": "PreTrainedTokenizerFast", + "chat_template": "{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside tags, and then provide your solution or response to the problem.' %}\n{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %}\n{%- if not thinking is defined %}{% set thinking = false %}{% endif %}\n{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %}\n{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %}\n{%- if tools %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- system_prompt }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou are a function calling AI model. You may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": \\\"\\\", \\\"arguments\\\": }\\n<|eot_id|>\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n\\n' + messages[0]['content'] + '<|eot_id|>' }}\n {%- else %}\n {{- bos_token + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_prompt + '<|eot_id|>' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n\\n' + message.content + '<|eot_id|>' }}\n {%- elif (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n' }}\n {%- if message.content %}\n {%- set content = message['content'] -%}\n {%- if thinking %}\n {%- if not keep_cots %}\n {%- set content = ' ' + content.split('', 1)[1] -%}\n {%- endif %}\n {%- endif %}\n {{- '\\n' + content + '<|eot_id|>' }}\n {%- endif %}\n {%- elif message.role == \"assistant\" %}\n {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\\n' }}\n {%- if message.content %}\n {%- set content = message['content'] -%}\n {%- if thinking %}\n {%- if not keep_cots %}\n {%- set content = ' ' + content.split('', 1)[1] -%}\n {%- endif %}\n {%- endif %}\n {{- '\\n' + content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|eot_id|>' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|eot_id|>' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n" +} \ No newline at end of file