commit d5f7e555f793e2b6495cfb1d7c421e1f91b06ee8 Author: ModelHub XC Date: Tue Aug 25 21:04:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: tokyotech-llm/Qwen3-Swallow-8B-CPT-v0.2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..714daca --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* 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 + +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00005.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..aeb0630 --- /dev/null +++ b/LICENSE @@ -0,0 +1,203 @@ + + 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 + Copyright 2026 Swallow LLM Team + + 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..03a00ed --- /dev/null +++ b/README.md @@ -0,0 +1,275 @@ +--- +language: +- en +- ja +license: apache-2.0 +datasets: +- tokyotech-llm/swallow-math-v2 +- tokyotech-llm/swallow-code-v2 +- tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1 +- tokyotech-llm/lmsys-chat-1m-synth +library_name: transformers +pipeline_tag: text-generation +model_type: null +--- + +# Qwen3-Swallow + +![logo](./qwen3-swallow.png) + +**Qwen3-Swallow v0.2** is a family of large language models available in **8B**, **30B-A3B**, and **32B** parameter sizes. Built as bilingual Japanese-English models, they were developed through Continual Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Reinforcement Learning with Verifiable Rewards (RLVR) based on the Qwen3 [Yang, 2025]. + +In addition to enhancing Japanese language proficiency and Japanese-English translation capabilities, we significantly improved or maintained performance on math and coding tasks during CPT by using high-quality math and code datasets with reasoning traces, along with custom-built datasets during SFT. Subsequently, we further improved the models' math and coding performance by enhancing reasoning capabilities through RLVR. + +- [Qwen3-Swallow Project Page](https://swallow-llm.github.io/qwen3-swallow.en.html) + +> [!NOTE] +> Please note that Qwen3-Swallow v0.1 is a skipped version number. + +## Highlights +* **Bilingual Proficiency:** Highly optimized for both Japanese and English. +* **Retained STEM Performance:** Strategic CPT and SFT pipelines successfully prevented catastrophic forgetting in mathematics and coding. +* **Enhanced Reasoning:** Achieved reasoning performance on par with the original Qwen3 models, and even surpassing them in some tasks. + +# Release History + +- **Feb 20, 2026**: Released [Qwen3-Swallow](https://huggingface.co/collections/tokyotech-llm/qwen3-swallow-v02) and [GPT-OSS-Swallow](https://huggingface.co/collections/tokyotech-llm/gpt-oss-swallow-v01). +- **Feb 23, 2026**: We made the GPTQ-quantized models private due to significant performance degradation. Please use the AWQ-quantized model instead. + +## HF Model Family + +We are releasing nine Qwen3-Swallow models: three each for CPT, SFT, and RL models. +Quantized versions of RL models are also available. +The complete list is as follows: + +### CPT models + +- [Qwen3 Swallow 8B CPT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-8B-CPT-v0.2) +- [Qwen3 Swallow 30B-A3B CPT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-30B-A3B-CPT-v0.2) +- [Qwen3 Swallow 32B CPT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-CPT-v0.2) + +### SFT models + +- [Qwen3 Swallow 8B SFT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-8B-SFT-v0.2) +- [Qwen3 Swallow 30B-A3B SFT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-30B-A3B-SFT-v0.2) +- [Qwen3 Swallow 32B SFT v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-SFT-v0.2) + +### RL models + +- [Qwen3 Swallow 8B RL v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-8B-RL-v0.2) +- [Qwen3 Swallow 30B-A3B RL v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2) +- [Qwen3 Swallow 32B RL v0.2](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2) + +### Quantized models + +- [Qwen3 Swallow 8B RL v0.2 AWQ-INT4](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-8B-RL-v0.2-AWQ-INT4) +- ~~Qwen3 Swallow 8B RL v0.2 GPTQ-INT4~~ +- [Qwen3 Swallow 30B-A3B RL v0.2 AWQ-INT4](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-30B-A3B-RL-v0.2-AWQ-INT4) +- ~~Qwen3 Swallow 30B-A3B RL v0.2 GPTQ-INT4~~ +- [Qwen3 Swallow 32B RL v0.2 AWQ-INT4](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2-AWQ-INT4) +- ~~Qwen3 Swallow 32B RL v0.2 GPTQ-INT4~~ + + +## Model Details + +- **Model type**: Please refer to [Qwen3 Technical Report](https://arxiv.org/abs/2505.09388) for details on the model architecture. +- **Language(s)**: Japanese, English +- **Tokenizer**: Please refer to [Qwen3 Technical Report](https://arxiv.org/abs/2505.09388) for details on the tokenizer. +- **Contact**: swallow[at]nlp.c.titech.ac.jp + +## Model Performance + +For comprehensive details on the evaluation tasks and the resulting scores, please refer to the [Swallow LLM Leaderboard](https://swallow-llm.github.io/leaderboard/). + +### Japanese tasks + +![Japanese Performance](./figure/qwen3-swallow-8b-cpt_ja_en.svg) + + +### English tasks + +![Japanese Performance](./figure/qwen3-swallow-8b-cpt_en_en.svg) + +## Usage + +### vLLM +> [!TIP] +> This model has been primarily debugged and evaluated using vLLM. +> For the most reliable and reproducible behavior, we strongly recommend running inference with vLLM. + +vLLM recommends using uv to manage the Python environment. + +```sh +uv venv --python 3.12 --seed +source .venv/bin/activate +uv pip install vllm +``` + +The following command will automatically download the model and start the server. +```sh +vllm serve tokyotech-llm/Qwen3-Swallow-8B-CPT-v0.2 --reasoning-parser qwen3 +``` +Commonly used options include: +- `--port` : Port number for the API server (default: 8000) +- `--tensor-parallel-size` : Number of GPUs for tensor parallelism (eg., 2 means using 2 GPUs for tensor parallelism) +- `--gpu-memory-utilization` : The fraction of GPU memory to be used for the model executor, which can range from 0 to 1.(e.g., 0.9 means using up to 90% of GPU memory) +- `--max-model-len` : Model context length of prompts + outputs.(eg., 32768) + +For the full list of available options, please refer to the official documentation: +https://docs.vllm.ai/en/stable/cli/serve/ + +Once the server is running, you can send requests using the OpenAI-compatible API: +```python +from openai import OpenAI +# Note: Replace with the actual model path/name you are using +model_name = "tokyotech-llm/Qwen3-Swallow-8B-CPT-v0.2" +client = OpenAI( + base_url="http://localhost:8000/v1", + api_key="EMPTY" +) +result = client.chat.completions.create( + model=model_name, + messages=[ + {"role": "user", "content": "Create a casual one-day Tokyo itinerary in Japanese."} + ], + max_tokens=4096, + temperature=0.6, + top_p=0.95, + extra_body={ + "top_k": 20, + "min_p": 0, + } +) +print("Reasoning:") +print(result.choices[0].message.reasoning) +print("\nResponse:") +print(result.choices[0].message.content) +``` + +### Best Practices + +We recommend specifying following generation parameters: Temperature=0.6, TopP=0.95, TopK=20, and MinP=0, which are the default values specified in `generation_config.json`. +You may omit manually specifying these parameters when using inference frameworks or clients that respect `generation_config.json` by default. +We also recommend specifying a max context length of 32,768 or less. + +### Unvalidated use cases + +- **Tool Use**: Please note that Qwen3-Swallow has not been explicitly trained for Tool Use (Function Calling). Users wishing to utilize Tool Use capabilities should consider performing custom post-training. + +- **Reasoning Toggle**: Qwen3-Swallow does not support toggling a "Reasoning ON/OFF" feature. Both the SFT and RL models are designed to perform reasoning by default. + +## Training Datasets + +### CPT (Continual Pre-Training) + +The following datasets were used for Continual Pre-Training (CPT). +Training was conducted using NVIDIA [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) with a context size of 32K (32,768) over a total of 209.7 billion tokens. + +#### Japanese and Japanese-English Parallel Corpus + +- [Japanese Wikipedia 2503](https://dumps.wikimedia.org/other/cirrussearch) +- [Swallow Corpus Version 3.2](https://arxiv.org/abs/2404.17733) +- [Swallow Corpus Version 3.2 QA](https://arxiv.org/abs/2404.17733) (synthetic QA-format text using gpt-oss-120b) +- [Laboro ParaCorpus](https://github.com/laboroai/Laboro-ParaCorpus) +- [Kaken ParaCorpus(Ja-En)](https://huggingface.co/datasets/hpprc/kaken-trans-ja-en) + +#### English Corpus +- [English Wikipedia 2503](https://dumps.wikimedia.org/other/cirrussearch) +- [Cosmopedia](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia) +- [Nemotron-CC](https://arxiv.org/abs/2412.02595)(2010-2024) high quality actual subset + +#### Math, Code +- [Swallow Code Version 2](https://huggingface.co/datasets/tokyotech-llm/swallow-code-v2) +- [Swallow Code Version 2 Q&A](https://huggingface.co/datasets/tokyotech-llm/swallow-code-v2) +- [Swallow Math Version 2](https://huggingface.co/datasets/tokyotech-llm/swallow-math-v2) +- [Swallow Math Version 2 Q&A](https://huggingface.co/datasets/tokyotech-llm/swallow-math-v2) + +#### STEM, Reasoning, and General Chat +- [GPT-OSS-LMSYS-Chat-1M-Synth-Ja](https://huggingface.co/datasets/tokyotech-llm/lmsys-chat-1m-synth) +- [GPT-OSS-LMSYS-Chat-1M-Synth-En](https://huggingface.co/datasets/tokyotech-llm/lmsys-chat-1m-synth) +- [Swallow-Nemotron-Post-Training-Dataset-v1](https://huggingface.co/datasets/tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1) (math, code, stem) + +### SFT (Supervised Fine-Tuning) +The following datasets were used for Supervised Fine-Tuning (SFT). +SFT was conducted using NVIDIA [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) with a context size of 32K (32,768). The training dataset sizes were as follows: 2.1M samples for 8B model, and 1.1M samples for both 30B-A3B and 32B models. + +- [GPT-OSS-LMSYS-Chat-1M-Synth-Ja](https://huggingface.co/datasets/tokyotech-llm/lmsys-chat-1m-synth): approximately 300k samples + - We excuded the conversations containing personally identifiable information. +- [GPT-OSS-LMSYS-Chat-1M-Synth-En](https://huggingface.co/datasets/tokyotech-llm/lmsys-chat-1m-synth): approximately 300k samples + - We excuded the conversations containing personally identifiable information. +- [Swallow-Nemotron-Post-Training-Dataset-v1](https://huggingface.co/datasets/tokyotech-llm/Swallow-Nemotron-Post-Training-Dataset-v1) (math, code, stem) + + +### RLVR +The following datasets were used for RLVR. +RLVR was conducted using [slime](https://github.com/THUDM/slime). During RL training, the maximum number of output tokens was set to 24,576 (input prompt tokens are not included). + + +- Math subset of [allenai/Dolci-Think-RL-7B](https://huggingface.co/datasets/allenai/Dolci-Think-RL-7B) + +### Quantization + +We provide AWQ-INT4 quantized variants of the RL models. +We generated outputs from RL dataset prompts, validated them, and used only complete, well-formed generations (excluding poor or incomplete outputs) for quantization calibration. + +## Risks and Limitations + +The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations. + +## Acknowledgements + +We thank Qwen Team for releasing Qwen3 under a generous open license. + + +This work is based on results obtained from a project, JPNP25006, subsidized by the New Energy and Industrial Technology Development Organization (NEDO). + + +This work was supported by the "R&D Hub Aimed at Ensuring Transparency and Reliability of Generative AI Models" project of the Ministry of Education, Culture, Sports, Science and Technology. + + +We used ABCI 3.0 provided by AIST and AIST Solutions with support from "ABCI 3.0 Development Acceleration Use". + + +This study was carried out using the TSUBAME4.0 supercomputer at Institute of Science Tokyo. + +## License + +[Apache license 2.0](./LICENSE) + +## Authors + +[Swallow LLM](https://swallow-llm.github.io/index.en.html) + +## How to cite + +If you find our work helpful, please feel free to cite these papers. +**The Qwen3-Swallow and GPT-OSS-Swallow Technical Paper (Training Details) will be released in March.** + +### Continual Pre-Training + +``` +@inproceedings{ + fujii2024continual, + title={Continual Pre-Training for Cross-Lingual {LLM} Adaptation: Enhancing Japanese Language Capabilities}, + author={Kazuki Fujii and Taishi Nakamura and Mengsay Loem and Hiroki Iida and Masanari Ohi and Kakeru Hattori and Hirai Shota and Sakae Mizuki and Rio Yokota and Naoaki Okazaki}, + booktitle={First Conference on Language Modeling}, + year={2024} +} +``` + +### Supervised Fine-Tuning + +``` +@inproceedings{ + ma2025building, + title={Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models}, + author={Youmi Ma and Sakae Mizuki and Kazuki Fujii and Taishi Nakamura and Masanari Ohi and Hinari Shimada and Taihei Shiotani and Koshiro Saito and Koki Maeda and Kakeru Hattori and Takumi Okamoto and Shigeki Ishida and Rio Yokota and Hiroya Takamura and Naoaki Okazaki}, + booktitle={Second Conference on Language Modeling}, + year={2025} +} +``` + + +### References + +[Yang, 2025] Alibaba. [Qwen3 Technical Report](https://arxiv.org/abs/2505.09388), arxiv:2505.09388. \ No newline at end of file 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..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- 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 message.content is string 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.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.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' }} + {{- 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..17dba5b --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "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" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "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": true, + "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/figure/qwen3-swallow-8b-cpt_en_en.svg b/figure/qwen3-swallow-8b-cpt_en_en.svg new file mode 100644 index 0000000..c145dc1 --- /dev/null +++ b/figure/qwen3-swallow-8b-cpt_en_en.svg @@ -0,0 +1,160 @@ + + +
+ +
NLI (HellaSwag)NLI (HellaSwag)NLU and reasoning (MMLU-Pro)NLU and reasoning (MMLU-Pro)Science (GPQA)Science (GPQA)Math (MATH-500)Math (MATH-500)Math (AIME 2024-2025)Math (AIME 2024-2025)Coding (LCB)Coding (LCB)AverageAverage1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Llama 3.1 Swallow 8B Instruct v0.5
DeepSeek-R1-Distill-Llama-8B
Olmo 3 7B Think
Qwen3-8B
Qwen3-Swallow-8B-CPT-v0.2
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-cpt_en_ja.svg b/figure/qwen3-swallow-8b-cpt_en_ja.svg new file mode 100644 index 0000000..7a52843 --- /dev/null +++ b/figure/qwen3-swallow-8b-cpt_en_ja.svg @@ -0,0 +1,160 @@ + + +
+ +
自然言語推論 (HellaSwag)自然言語推論 (HellaSwag)言語理解と推論 (MMLU-Pro)言語理解と推論 (MMLU-Pro)科学 (GPQA)科学 (GPQA)数学 (MATH-500)数学 (MATH-500)数学 (AIME 2024-2025)数学 (AIME 2024-2025)コーディング (LCB)コーディング (LCB)平均平均1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Llama 3.1 Swallow 8B Instruct v0.5
DeepSeek-R1-Distill-Llama-8B
Olmo 3 7B Think
Qwen3-8B
Qwen3-Swallow-8B-CPT-v0.2
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-cpt_ja_en.svg b/figure/qwen3-swallow-8b-cpt_ja_en.svg new file mode 100644 index 0000000..f21c87c --- /dev/null +++ b/figure/qwen3-swallow-8b-cpt_ja_en.svg @@ -0,0 +1,160 @@ + + +
+ +
Q&A (JamC-QA)Q&A (JamC-QA)En-Ja (WMT20)En-Ja (WMT20)Ja-En (WMT20)Ja-En (WMT20)NLU and reasoning (MMLU-ProX)NLU and reasoning (MMLU-ProX)Science (GPQA, Japanese)Science (GPQA, Japanese)Math (MATH-100)Math (MATH-100)Coding (JHumanEval)Coding (JHumanEval)AverageAverage1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Llama 3.1 Swallow 8B Instruct v0.5
DeepSeek-R1-Distill-Llama-8B
Olmo 3 7B Think
Qwen3-8B
Qwen3-Swallow-8B-CPT-v0.2
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-cpt_ja_ja.svg b/figure/qwen3-swallow-8b-cpt_ja_ja.svg new file mode 100644 index 0000000..d06ee15 --- /dev/null +++ b/figure/qwen3-swallow-8b-cpt_ja_ja.svg @@ -0,0 +1,160 @@ + + +
+ +
質問応答 (JamC-QA)質問応答 (JamC-QA)英日翻訳 (WMT20)英日翻訳 (WMT20)日英翻訳 (WMT20)日英翻訳 (WMT20)言語理解と推論 (MMLU-ProX)言語理解と推論 (MMLU-ProX)科学 (GPQA, 日本語)科学 (GPQA, 日本語)数学 (MATH-100)数学 (MATH-100)コーディング (JHumanEval)コーディング (JHumanEval)平均平均1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Llama 3.1 Swallow 8B Instruct v0.5
DeepSeek-R1-Distill-Llama-8B
Olmo 3 7B Think
Qwen3-8B
Qwen3-Swallow-8B-CPT-v0.2
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-series_en_en.svg b/figure/qwen3-swallow-8b-series_en_en.svg new file mode 100644 index 0000000..862b671 --- /dev/null +++ b/figure/qwen3-swallow-8b-series_en_en.svg @@ -0,0 +1,160 @@ + + +
+ +
NLI (HellaSwag)NLI (HellaSwag)NLU and reasoning (MMLU-Pro)NLU and reasoning (MMLU-Pro)Science (GPQA)Science (GPQA)Math (MATH-500)Math (MATH-500)Math (AIME 2024-2025)Math (AIME 2024-2025)Coding (LCB)Coding (LCB)AverageAverage1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Qwen3-8B-Base
Qwen3-Swallow-8B-CPT-v0.2
Qwen3-Swallow-8B-SFT-v0.2
Qwen3-Swallow-8B-RL-v0.2
Qwen3-8B
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-series_en_ja.svg b/figure/qwen3-swallow-8b-series_en_ja.svg new file mode 100644 index 0000000..4b85680 --- /dev/null +++ b/figure/qwen3-swallow-8b-series_en_ja.svg @@ -0,0 +1,160 @@ + + +
+ +
自然言語推論 (HellaSwag)自然言語推論 (HellaSwag)言語理解と推論 (MMLU-Pro)言語理解と推論 (MMLU-Pro)科学 (GPQA)科学 (GPQA)数学 (MATH-500)数学 (MATH-500)数学 (AIME 2024-2025)数学 (AIME 2024-2025)コーディング (LCB)コーディング (LCB)平均平均1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Qwen3-8B-Base
Qwen3-Swallow-8B-CPT-v0.2
Qwen3-Swallow-8B-SFT-v0.2
Qwen3-Swallow-8B-RL-v0.2
Qwen3-8B
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-series_ja_en.svg b/figure/qwen3-swallow-8b-series_ja_en.svg new file mode 100644 index 0000000..5ea1044 --- /dev/null +++ b/figure/qwen3-swallow-8b-series_ja_en.svg @@ -0,0 +1,160 @@ + + +
+ +
Q&A (JamC-QA)Q&A (JamC-QA)En-Ja (WMT20)En-Ja (WMT20)Ja-En (WMT20)Ja-En (WMT20)NLU and reasoning (MMLU-ProX)NLU and reasoning (MMLU-ProX)Science (GPQA, Japanese)Science (GPQA, Japanese)Math (MATH-100)Math (MATH-100)Coding (JHumanEval)Coding (JHumanEval)AverageAverage1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Qwen3-8B-Base
Qwen3-Swallow-8B-CPT-v0.2
Qwen3-Swallow-8B-SFT-v0.2
Qwen3-Swallow-8B-RL-v0.2
Qwen3-8B
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/figure/qwen3-swallow-8b-series_ja_ja.svg b/figure/qwen3-swallow-8b-series_ja_ja.svg new file mode 100644 index 0000000..e422852 --- /dev/null +++ b/figure/qwen3-swallow-8b-series_ja_ja.svg @@ -0,0 +1,160 @@ + + +
+ +
質問応答 (JamC-QA)質問応答 (JamC-QA)英日翻訳 (WMT20)英日翻訳 (WMT20)日英翻訳 (WMT20)日英翻訳 (WMT20)言語理解と推論 (MMLU-ProX)言語理解と推論 (MMLU-ProX)科学 (GPQA, 日本語)科学 (GPQA, 日本語)数学 (MATH-100)数学 (MATH-100)コーディング (JHumanEval)コーディング (JHumanEval)平均平均1.01.00.80.80.60.60.40.40.20.20.00.0Chart
Qwen3-8B-Base
Qwen3-Swallow-8B-CPT-v0.2
Qwen3-Swallow-8B-SFT-v0.2
Qwen3-Swallow-8B-RL-v0.2
Qwen3-8B
Download SVG
Download PNG
Download CSV
+
+ + \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b9efe0a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "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", + "trust_remote_code": false +} 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-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..f819a43 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba0d0d94897b21c05bf2a55f7b62260a8aa13ec991282b57bd0f24966191f18a +size 3996250720 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..0e93a23 --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be95820dc3e64c9a88e856562e4e88c1e83c9efec0db5219c4ce364bdb489021 +size 3993160000 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..2576e12 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be88986834e7c2e5b73f45a5e02a1c3283a2d38125d99a852513cd9774e539f9 +size 3959604736 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..4df6633 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3efbb8c8c1183962e28becc0e7be0bc0bbd5eda5a0ebf1be096552209cf30861 +size 3187841360 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..292ed23 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba0f86cffc46c22a7b3351cf171cb74b3425c8d467dfff80c50328adff8cc15 +size 1244659808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0fd2d13 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_size": 16381470720 + }, + "weight_map": { + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "lm_head.weight": "model-00005-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.norm.weight": "model-00004-of-00005.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors" + } +} \ No newline at end of file diff --git a/qwen3-swallow.png b/qwen3-swallow.png new file mode 100644 index 0000000..5681d26 Binary files /dev/null and b/qwen3-swallow.png differ diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /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": "<|endoftext|>", + "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..ad66c3a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "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": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} 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