From 17bf69f29d1fd19761e7b2e8341f8b8973ce0e59 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 8 Aug 2026 12:09:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Skyorca/JT-DA-Safe Source: Original Platform --- .gitattributes | 77 ++++++ LICENSE | 202 ++++++++++++++ README.md | 25 ++ added_tokens.json | 28 ++ chat_template.jinja | 85 ++++++ config.json | 72 +++++ configuration.json | 1 + generation_config.json | 13 + latest | 1 + merges.txt | 3 + model-00001-of-00007.safetensors | 3 + model-00002-of-00007.safetensors | 3 + model-00003-of-00007.safetensors | 3 + model-00004-of-00007.safetensors | 3 + model-00005-of-00007.safetensors | 3 + model-00006-of-00007.safetensors | 3 + model-00007-of-00007.safetensors | 3 + model.safetensors.index.json | 451 +++++++++++++++++++++++++++++++ special_tokens_map.json | 31 +++ tokenizer.json | 3 + tokenizer_config.json | 240 ++++++++++++++++ trainer_state.json | 186 +++++++++++++ training_args.bin | 3 + vocab.json | 3 + 24 files changed, 1445 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 latest create mode 100644 merges.txt create mode 100644 model-00001-of-00007.safetensors create mode 100644 model-00002-of-00007.safetensors create mode 100644 model-00003-of-00007.safetensors create mode 100644 model-00004-of-00007.safetensors create mode 100644 model-00005-of-00007.safetensors create mode 100644 model-00006-of-00007.safetensors create mode 100644 model-00007-of-00007.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 trainer_state.json create mode 100644 training_args.bin create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..580ec60 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,77 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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 +model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text + +model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text + + + +training_args.bin filter=lfs diff=lfs merge=lfs -text +"/model-00001-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00002-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00003-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00004-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00005-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00006-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text +"/model-00007-of-00007.safetensors" filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..6634c8c --- /dev/null +++ b/LICENSE @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2024 Alibaba Cloud + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..9dfaafe --- /dev/null +++ b/README.md @@ -0,0 +1,25 @@ +# JT-DA-Safe + +JT-DA-Safe for Social Recognition Safety. + +This repository provides the initial model artifacts for the JT-DA-Safe project. The project focuses on research, evaluation, supervised fine-tuning, and reinforcement learning for social recognition safety. + +## Intended Use + +- Social recognition safety research +- Safety-oriented model evaluation +- Supervised fine-tuning experiments +- Reinforcement learning experiments +- Internal research and development + +## Repository Contents + +The repository contains model weights, configuration files, tokenizer files, and generation settings required for model loading and inference. + +## Limitations + +Model outputs may contain inaccurate, biased, unsafe, or unexpected content. Results should be reviewed before being used in safety-sensitive or production scenarios. + +## Notice + +This repository is intended for research and evaluation purposes. Users are responsible for validating model behavior and complying with applicable laws, regulations, and platform requirements. diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..699ff8d --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,85 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou 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<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set content = message.content %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is defined and message.reasoning_content is not none %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in message.content %} + {%- set content = message.content.split('')[-1].lstrip('\n') %} + {%- set reasoning_content = message.content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8cd51e7 --- /dev/null +++ b/config.json @@ -0,0 +1,72 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 17408, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 40, + "model_type": "qwen3", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..98e0755 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.57.3" +} diff --git a/latest b/latest new file mode 100644 index 0000000..eef1304 --- /dev/null +++ b/latest @@ -0,0 +1 @@ +global_step210 \ No newline at end of file diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..bcea1c6 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f51bb02face6e456a5c7f79061011a1c76613b60282434c6660f19689e5fe8 +size 4865613360 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..cc9ee3d --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19761b696beb2f5aded5d8dec437c201746bd4acce6296b42230e535c858f544 +size 3680666936 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..06b80ff --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92595ee0154c739c6f9e5238b8dd724bd140c7ab66265633042d6d50221d757a +size 3642546848 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..4d961a4 --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c9f94f3240fac9ac2c60bd1ad9d03257c1ed84a7dc1810877da006a0dac76f +size 4900862472 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..0d9eea7 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec95cc6e0891c5701c6d39a93138c1826294d6d10af5caa6a25fa126ab05472 +size 4907524064 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..31289d5 --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c5079b5a75ade5cba4f32cfe67ca49885516f7e16b243677a53e3ad7452e89 +size 4980880888 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..a0585d7 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeefd590d766190dd663910c820ffd9dcc3eed4954957e646045200118b9b8d +size 2558571008 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d613d6e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,451 @@ +{ + "metadata": { + "total_parameters": 14768307200, + "total_size": 29536614400 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00007.safetensors", + "model.embed_tokens.weight": "model-00004-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00003-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00003-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00007-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00007-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00007-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.34.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00003-of-00007.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.36.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.38.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00004-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00006-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.norm.weight": "model-00002-of-00007.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0209709 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..f6fad92 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,186 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3893805309734513, + "eval_steps": 5, + "global_step": 40, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.17699115044247787, + "grad_norm": 1.4092590808868408, + "learning_rate": 8.888888888888888e-07, + "loss": 0.7311, + "step": 5 + }, + { + "epoch": 0.17699115044247787, + "eval_runtime": 463.9821, + "eval_samples_per_second": 0.455, + "eval_sombench_accuracy": 0.6066350710900474, + "eval_sombench_dim1_accuracy": 0.5168539325842697, + "eval_sombench_dim2_accuracy": 0.675, + "eval_sombench_dim3_accuracy": 0.6666666666666666, + "eval_sombench_leaderboard_score": 60.65, + "eval_steps_per_second": 0.015, + "step": 5 + }, + { + "epoch": 0.35398230088495575, + "grad_norm": 1.3532044887542725, + "learning_rate": 2e-06, + "loss": 0.7118, + "step": 10 + }, + { + "epoch": 0.35398230088495575, + "eval_runtime": 123.0467, + "eval_samples_per_second": 1.715, + "eval_sombench_accuracy": 0.6018957345971564, + "eval_sombench_dim1_accuracy": 0.5168539325842697, + "eval_sombench_dim2_accuracy": 0.6625, + "eval_sombench_dim3_accuracy": 0.6666666666666666, + "eval_sombench_leaderboard_score": 60.18, + "eval_steps_per_second": 0.057, + "step": 10 + }, + { + "epoch": 0.5309734513274337, + "grad_norm": 1.273472785949707, + "learning_rate": 1.9781476007338054e-06, + "loss": 0.7233, + "step": 15 + }, + { + "epoch": 0.5309734513274337, + "eval_runtime": 120.8118, + "eval_samples_per_second": 1.747, + "eval_sombench_accuracy": 0.6066350710900474, + "eval_sombench_dim1_accuracy": 0.4943820224719101, + "eval_sombench_dim2_accuracy": 0.6875, + "eval_sombench_dim3_accuracy": 0.6904761904761905, + "eval_sombench_leaderboard_score": 60.65, + "eval_steps_per_second": 0.058, + "step": 15 + }, + { + "epoch": 0.7079646017699115, + "grad_norm": 1.3325337171554565, + "learning_rate": 1.9135454576426007e-06, + "loss": 0.7059, + "step": 20 + }, + { + "epoch": 0.7079646017699115, + "eval_runtime": 111.9794, + "eval_samples_per_second": 1.884, + "eval_sombench_accuracy": 0.5924170616113744, + "eval_sombench_dim1_accuracy": 0.47191011235955055, + "eval_sombench_dim2_accuracy": 0.675, + "eval_sombench_dim3_accuracy": 0.6904761904761905, + "eval_sombench_leaderboard_score": 59.22, + "eval_steps_per_second": 0.063, + "step": 20 + }, + { + "epoch": 0.8849557522123894, + "grad_norm": 1.2877130508422852, + "learning_rate": 1.8090169943749474e-06, + "loss": 0.6969, + "step": 25 + }, + { + "epoch": 0.8849557522123894, + "eval_runtime": 110.0958, + "eval_samples_per_second": 1.917, + "eval_sombench_accuracy": 0.6161137440758294, + "eval_sombench_dim1_accuracy": 0.4943820224719101, + "eval_sombench_dim2_accuracy": 0.7, + "eval_sombench_dim3_accuracy": 0.7142857142857143, + "eval_sombench_leaderboard_score": 61.59, + "eval_steps_per_second": 0.064, + "step": 25 + }, + { + "epoch": 1.0353982300884956, + "grad_norm": 1.266132116317749, + "learning_rate": 1.669130606358858e-06, + "loss": 0.6947, + "step": 30 + }, + { + "epoch": 1.0353982300884956, + "eval_runtime": 107.7201, + "eval_samples_per_second": 1.959, + "eval_sombench_accuracy": 0.6208530805687204, + "eval_sombench_dim1_accuracy": 0.5280898876404494, + "eval_sombench_dim2_accuracy": 0.675, + "eval_sombench_dim3_accuracy": 0.7142857142857143, + "eval_sombench_leaderboard_score": 62.07, + "eval_steps_per_second": 0.065, + "step": 30 + }, + { + "epoch": 1.2123893805309733, + "grad_norm": 1.20622718334198, + "learning_rate": 1.5e-06, + "loss": 0.6717, + "step": 35 + }, + { + "epoch": 1.2123893805309733, + "eval_runtime": 109.6785, + "eval_samples_per_second": 1.924, + "eval_sombench_accuracy": 0.6208530805687204, + "eval_sombench_dim1_accuracy": 0.5168539325842697, + "eval_sombench_dim2_accuracy": 0.6875, + "eval_sombench_dim3_accuracy": 0.7142857142857143, + "eval_sombench_leaderboard_score": 62.07, + "eval_steps_per_second": 0.064, + "step": 35 + }, + { + "epoch": 1.3893805309734513, + "grad_norm": 1.228661298751831, + "learning_rate": 1.3090169943749473e-06, + "loss": 0.6556, + "step": 40 + }, + { + "epoch": 1.3893805309734513, + "eval_runtime": 108.9835, + "eval_samples_per_second": 1.936, + "eval_sombench_accuracy": 0.6255924170616114, + "eval_sombench_dim1_accuracy": 0.5168539325842697, + "eval_sombench_dim2_accuracy": 0.6875, + "eval_sombench_dim3_accuracy": 0.7380952380952381, + "eval_sombench_leaderboard_score": 62.54, + "eval_steps_per_second": 0.064, + "step": 40 + } + ], + "logging_steps": 5, + "max_steps": 84, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 5, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.597738925865042e+17, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..fd2c0fa --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc31582b9df08139a0d710bb320de4b50e0ba669f1f94a15077d994cedff268 +size 7416 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833