diff --git a/README.md b/README.md index 57e152405..901d3904d 100644 --- a/README.md +++ b/README.md @@ -319,7 +319,7 @@ Read technical notes: | [Pixtral](https://huggingface.co/mistralai) | 12B | pixtral | | [Qwen2 (Code/Math/MoE/QwQ)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen | | [Qwen3 (MoE/Instruct/Thinking/Next)](https://huggingface.co/Qwen) | 0.6B/1.7B/4B/8B/14B/32B/80B/235B | qwen3/qwen3_nothink | -| [Qwen3.5](https://huggingface.co/Qwen) | 27B/35B/122B/397B | qwen3_5 | +| [Qwen3.5](https://huggingface.co/Qwen) | 0.8B/2B/4B/9B/27B/35B/122B/397B | qwen3_5 | | [Qwen2-Audio](https://huggingface.co/Qwen) | 7B | qwen2_audio | | [Qwen2.5-Omni](https://huggingface.co/Qwen) | 3B/7B | qwen2_omni | | [Qwen3-Omni](https://huggingface.co/Qwen) | 30B | qwen3_omni | diff --git a/README_zh.md b/README_zh.md index ba2a1c546..3fa64854f 100644 --- a/README_zh.md +++ b/README_zh.md @@ -321,7 +321,7 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc | [Pixtral](https://huggingface.co/mistralai) | 12B | pixtral | | [Qwen2 (Code/Math/MoE/QwQ)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen | | [Qwen3 (MoE/Instruct/Thinking/Next)](https://huggingface.co/Qwen) | 0.6B/1.7B/4B/8B/14B/32B/80B/235B | qwen3/qwen3_nothink | -| [Qwen3.5](https://huggingface.co/Qwen) | 27B/35B/122B/397B | qwen3_5 | +| [Qwen3.5](https://huggingface.co/Qwen) | 0.8B/2B/4B/9B/27B/35B/122B/397B | qwen3_5 | | [Qwen2-Audio](https://huggingface.co/Qwen) | 7B | qwen2_audio | | [Qwen2.5-Omni](https://huggingface.co/Qwen) | 3B/7B | qwen2_omni | | [Qwen3-Omni](https://huggingface.co/Qwen) | 30B | qwen3_omni | diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py index c45e7c8f0..7e23e3162 100644 --- a/src/llamafactory/extras/constants.py +++ b/src/llamafactory/extras/constants.py @@ -2812,10 +2812,42 @@ register_model_group( register_model_group( models={ + "Qwen3.5-0.8B-Base": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-0.8B-Base", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-0.8B-Base", + }, + "Qwen3.5-2B-Base": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-2B-Base", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-2B-Base", + }, + "Qwen3.5-4B-Base": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-4B-Base", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-4B-Base", + }, + "Qwen3.5-9B-Base": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-9B-Base", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-9B-Base", + }, "Qwen3.5-35B-A3B-Base": { DownloadSource.DEFAULT: "Qwen/Qwen3.5-35B-A3B-Base", DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-35B-A3B-Base", }, + "Qwen3.5-0.8B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-0.8B", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-0.8B", + }, + "Qwen3.5-2B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-2B", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-2B", + }, + "Qwen3.5-4B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-4B", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-4B", + }, + "Qwen3.5-9B-Thinking": { + DownloadSource.DEFAULT: "Qwen/Qwen3.5-9B", + DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-9B", + }, "Qwen3.5-27B-Thinking": { DownloadSource.DEFAULT: "Qwen/Qwen3.5-27B", DownloadSource.MODELSCOPE: "Qwen/Qwen3.5-27B",