423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-03-03 18:25:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] support Qwen3.5 all series models (#10237)

Browse Source 
Co-authored-by: gatilin <gatilin@tencent.com>
Co-authored-by: Yaowei Zheng <hiyouga@buaa.edu.cn>
This commit is contained in:
Hertz
2026-03-03 17:34:59 +08:00
committed by GitHub
parent eb976d75a2
commit c0245c43fc
3 changed files with 34 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -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 |

2
README_zh.md
View File

@@ -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 |

32
src/llamafactory/extras/constants.py
View File

@@ -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",