h123fire

8*H20,8块H20 无法使用DPO训练qwen2.5-vl-7B模型，300帧视频理解

1

### Reminder - [x] I have read the above rules and searched the existing issues. ### System Info llamafactory-cli train \ --stage dpo \ --do_train True \ --model_name_or_path Qwen/Qwen2.5-VL-7B-Instruct \...

是否可以支持更长训练的训练，比如150K+的一些训练方法？

3

### Reminder - [x] I have read the above rules and searched the existing issues. ### Description 1 ### Pull Request _No response_

load qwen_image_edit_2509 error

6

### Checklist - [ ] 1. I have searched for related issues and FAQs (https://nunchaku.tech/docs/nunchaku/faq/faq.html) but was unable to find a solution. - [ ] 2. The issue persists in...