diff --git a/README.md b/README.md index c6d0e1a8..a4d4e47a 100644 --- a/README.md +++ b/README.md @@ -81,21 +81,23 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ ## Changelog +[24/11/27] We supported fine-tuning the **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** model and the **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** dataset. + [24/10/09] We supported downloading pre-trained models and datasets from the **[Modelers Hub](https://modelers.cn/models)**. See [this tutorial](#download-from-modelers-hub) for usage. -[24/09/19] We support fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models. +[24/09/19] We supported fine-tuning the **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** models. -[24/08/30] We support fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR. - -[24/08/27] We support **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training. - -[24/08/09] We support **[Adam-mini](https://github.com/zyushun/Adam-mini)** optimizer. See [examples](examples/README.md) for usage. Thank [@relic-yuexi](https://github.com/relic-yuexi)'s PR. +[24/08/30] We supported fine-tuning the **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** models. Thank [@simonJJJ](https://github.com/simonJJJ)'s PR.
Full Changelog -[24/07/04] We support [contamination-free packed training](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing). Use `neat_packing: true` to activate it. Thank [@chuan298](https://github.com/chuan298)'s PR. +[24/08/27] We supported **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**. Try `enable_liger_kernel: true` for efficient training. -[24/06/16] We support **[PiSSA](https://arxiv.org/abs/2404.02948)** algorithm. See [examples](examples/README.md) for usage. +[24/08/09] We supported **[Adam-mini](https://github.com/zyushun/Adam-mini)** optimizer. See [examples](examples/README.md) for usage. Thank [@relic-yuexi](https://github.com/relic-yuexi)'s PR. + +[24/07/04] We supported [contamination-free packed training](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing). Use `neat_packing: true` to activate it. Thank [@chuan298](https://github.com/chuan298)'s PR. + +[24/06/16] We supported **[PiSSA](https://arxiv.org/abs/2404.02948)** algorithm. See [examples](examples/README.md) for usage. [24/06/07] We supported fine-tuning the **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** and **[GLM-4](https://github.com/THUDM/GLM-4)** models. @@ -202,6 +204,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ | [Pixtral](https://huggingface.co/mistralai) | 12B | pixtral | | [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen | | [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl | +| [Skywork o1](https://huggingface.co/Skywork) | 8B | skywork_o1 | | [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | | [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | | [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai) | 1.5B/6B/9B/34B | yi | @@ -290,9 +293,10 @@ You also can add a custom chat template to [template.py](src/llamafactory/data/t - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction) - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo) - [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2) -- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub) - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered) - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1) +- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub) +- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k) - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) @@ -730,7 +734,7 @@ If you have a project that should be incorporated, please contact via email or c This repository is licensed under the [Apache-2.0 License](LICENSE). -Please follow the model licenses to use the corresponding model weights: [Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) +Please follow the model licenses to use the corresponding model weights: [Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [Skywork](https://huggingface.co/Skywork/Skywork-13B-base/blob/main/Skywork%20Community%20License.pdf) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) ## Citation diff --git a/README_zh.md b/README_zh.md index 9ba60c05..f075d488 100644 --- a/README_zh.md +++ b/README_zh.md @@ -82,18 +82,20 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272 ## 更新日志 +[24/11/27] 我们支持了 **[Skywork-o1](https://huggingface.co/Skywork/Skywork-o1-Open-Llama-3.1-8B)** 模型的微调和 **[OpenO1](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT)** 数据集。 + [24/10/09] 我们支持了从 **[魔乐社区](https://modelers.cn/models)** 下载预训练模型和数据集。详细用法请参照 [此教程](#从魔乐社区下载)。 [24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。 [24/08/30] 我们支持了 **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** 模型的微调。感谢 [@simonJJJ](https://github.com/simonJJJ) 的 PR。 +
展开日志 + [24/08/27] 我们支持了 **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**。请使用 `enable_liger_kernel: true` 来加速训练。 [24/08/09] 我们支持了 **[Adam-mini](https://github.com/zyushun/Adam-mini)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。 -
展开日志 - [24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。 [24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。 @@ -202,6 +204,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272 | [Pixtral](https://huggingface.co/mistralai) | 12B | pixtral | | [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen | | [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl | +| [Skywork o1](https://huggingface.co/Skywork) | 8B | skywork_o1 | | [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - | | [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse | | [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai) | 1.5B/6B/9B/34B | yi | @@ -290,9 +293,10 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272 - [STEM (zh)](https://huggingface.co/datasets/hfl/stem_zh_instruction) - [Ruozhiba (zh)](https://huggingface.co/datasets/hfl/ruozhiba_gpt4_turbo) - [Neo-sft (zh)](https://huggingface.co/datasets/m-a-p/neo_sft_phase2) -- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub) - [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered) - [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1) +- [WebInstructSub (en)](https://huggingface.co/datasets/TIGER-Lab/WebInstructSub) +- [OpenO1-SFT (en&zh)](https://huggingface.co/datasets/O1-OPEN/OpenO1-SFT) - [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k) - [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions) - [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de) @@ -729,7 +733,7 @@ run_name: test_run # 可选 本仓库的代码依照 [Apache-2.0](LICENSE) 协议开源。 -使用模型权重时，请遵循对应的模型协议：[Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) +使用模型权重时，请遵循对应的模型协议：[Baichuan 2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/blob/main/Community%20License%20for%20Baichuan%202%20Model.pdf) / [BLOOM](https://huggingface.co/spaces/bigscience/license) / [ChatGLM3](https://github.com/THUDM/ChatGLM3/blob/main/MODEL_LICENSE) / [Command R](https://cohere.com/c4ai-cc-by-nc-license) / [DeepSeek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/LICENSE-MODEL) / [Falcon](https://huggingface.co/tiiuae/falcon-180B/blob/main/LICENSE.txt) / [Gemma](https://ai.google.dev/gemma/terms) / [GLM-4](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE) / [Index](https://huggingface.co/IndexTeam/Index-1.9B/blob/main/LICENSE) / [InternLM2](https://github.com/InternLM/InternLM#license) / [Llama](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) / [Llama 2 (LLaVA-1.5)](https://ai.meta.com/llama/license/) / [Llama 3](https://llama.meta.com/llama3/license/) / [MiniCPM](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md) / [Mistral/Mixtral/Pixtral](LICENSE) / [OLMo](LICENSE) / [Phi-1.5/Phi-2](https://huggingface.co/microsoft/phi-1_5/resolve/main/Research%20License.docx) / [Phi-3](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE) / [Qwen](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) / [Skywork](https://huggingface.co/Skywork/Skywork-13B-base/blob/main/Skywork%20Community%20License.pdf) / [StarCoder 2](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) / [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) / [Yi](https://huggingface.co/01-ai/Yi-6B/blob/main/LICENSE) / [Yi-1.5](LICENSE) / [Yuan 2](https://github.com/IEIT-Yuan/Yuan-2.0/blob/main/LICENSE-Yuan) ## 引用 diff --git a/data/dataset_info.json b/data/dataset_info.json index 7cfb0e79..7c980b97 100644 --- a/data/dataset_info.json +++ b/data/dataset_info.json @@ -296,6 +296,14 @@ "response": "answer" } }, + "openo1_sft": { + "hf_hub_url": "llamafactory/OpenO1-SFT", + "ms_hub_url": "llamafactory/OpenO1-SFT", + "columns": { + "prompt": "prompt", + "response": "response" + } + }, "llava_1k_en": { "hf_hub_url": "BUAADreamer/llava-en-zh-2k", "subset": "en", diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py index 6054b7a6..33ba58a9 100644 --- a/src/llamafactory/data/template.py +++ b/src/llamafactory/data/template.py @@ -512,6 +512,7 @@ _register_template( ) +# copied from chatml template _register_template( name="chatml_de", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -578,6 +579,7 @@ _register_template( ) +# copied from chatml template _register_template( name="dbrx", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -728,6 +730,7 @@ _register_template( ) +# copied from llama2 template _register_template( name="llama2_zh", format_user=StringFormatter(slots=[{"bos_token"}, "[INST] {{content}} [/INST]"]), @@ -762,6 +765,7 @@ _register_template( ) +# copied from llama3 template _register_template( name="mllama", format_user=StringFormatter( @@ -789,6 +793,7 @@ _register_template( ) +# copied from vicuna template _register_template( name="llava", format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]), @@ -800,6 +805,7 @@ _register_template( ) +# copied from vicuna template _register_template( name="llava_next", format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]), @@ -811,6 +817,7 @@ _register_template( ) +# copied from llama3 template _register_template( name="llava_next_llama3", format_user=StringFormatter( @@ -838,6 +845,7 @@ _register_template( ) +# copied from mistral template _register_template( name="llava_next_mistral", format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]), @@ -846,6 +854,7 @@ _register_template( ) +# copied from chatml template _register_template( name="llava_next_qwen", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -860,6 +869,7 @@ _register_template( ) +# copied from chatml template _register_template( name="llava_next_yi", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -871,6 +881,7 @@ _register_template( ) +# copied from vicuna template _register_template( name="llava_next_video", format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]), @@ -882,6 +893,7 @@ _register_template( ) +# copied from mistral template _register_template( name="llava_next_video_mistral", format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]), @@ -890,6 +902,7 @@ _register_template( ) +# copied from chatml template _register_template( name="llava_next_video_yi", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -901,6 +914,23 @@ _register_template( ) +# copied from chatml template +_register_template( + name="marco", + format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), + format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]), + format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), + format_separator=EmptyFormatter(slots=["\n"]), + default_system=( + "你是一个经过良好训练的AI助手，你的名字是Marco-o1.由阿里国际数字商业集团的AI Business创造.\n## 重要！！！！！\n" + "当你回答问题时，你的思考应该在内完成，内输出你的结果。\n" + "应该尽可能是英文，但是有2个特例，一个是对原文中的引用，另一个是是数学应该使用markdown格式，内的输出需要遵循用户输入的语言。\n" + ), + stop_words=["<|im_end|>"], + replace_eos=True, +) + + _register_template( name="mistral", format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]), @@ -938,6 +968,7 @@ _register_template( ) +# copied from chatml template _register_template( name="opencoder", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -958,6 +989,7 @@ _register_template( ) +# copied from gemma template _register_template( name="paligemma", format_user=StringFormatter(slots=["user\n{{content}}\nmodel\n"]), @@ -1001,6 +1033,7 @@ _register_template( ) +# copied from chatml template _register_template( name="qwen", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -1014,6 +1047,7 @@ _register_template( ) +# copied from chatml template _register_template( name="qwen2_vl", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), @@ -1042,6 +1076,39 @@ _register_template( ) +# copied from llama3 template +_register_template( + name="skywork_o1", + format_user=StringFormatter( + slots=[ + ( + "<|start_header_id|>user<|end_header_id|>\n\n{{content}}<|eot_id|>" + "<|start_header_id|>assistant<|end_header_id|>\n\n" + ) + ] + ), + format_system=StringFormatter(slots=["<|start_header_id|>system<|end_header_id|>\n\n{{content}}<|eot_id|>"]), + format_observation=StringFormatter( + slots=[ + ( + "<|start_header_id|>tool<|end_header_id|>\n\n{{content}}<|eot_id|>" + "<|start_header_id|>assistant<|end_header_id|>\n\n" + ) + ] + ), + format_prefix=EmptyFormatter(slots=[{"bos_token"}]), + default_system=( + "You are Skywork-o1, a thinking model developed by Skywork AI, specializing in solving complex problems " + "involving mathematics, coding, and logical reasoning through deep thought. When faced with a user's request, " + "you first engage in a lengthy and in-depth thinking process to explore possible solutions to the problem. " + "After completing your thoughts, you then provide a detailed explanation of the solution process " + "in your response." + ), + stop_words=["<|eot_id|>"], + replace_eos=True, +) + + _register_template( name="solar", format_user=StringFormatter(slots=["### User:\n{{content}}\n\n### Assistant:\n"]), @@ -1127,6 +1194,7 @@ _register_template( ) +# copied from chatml template _register_template( name="yi", format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]), diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index 5fdb33c2..cde747cd 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -998,6 +998,17 @@ register_model_group( ) +register_model_group( + models={ + "Marco-o1-Chat": { + DownloadSource.DEFAULT: "AIDC-AI/Marco-o1", + DownloadSource.MODELSCOPE: "AIDC-AI/Marco-o1", + }, + }, + template="marco", +) + + register_model_group( models={ "MiniCPM-2B-SFT-Chat": { @@ -1912,6 +1923,16 @@ register_model_group( ) +register_model_group( + models={ + "Skywork-o1-Open-Llama-3.1-8B": { + DownloadSource.DEFAULT: "Skywork/Skywork-o1-Open-Llama-3.1-8B", + } + }, + template="skywork_o1", +) + + register_model_group( models={ "StarCoder2-3B": {