modelscope / modelscope/ms-swift
qwen3 sft的时候的think
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
swift框架是否有类似llamafactory在sft qwen3的时候的参数enable_thinking（此参数为True则会判断sft数据集中的input中是否有think\n\n/think标签，如果没有则会添加），swift框架能否用不带think标签的sft数据集进行sft qwen3，如果用不带think标签的sft训练数据，swift的处理框架是怎么样的？
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the ms-swift SFT handling for Qwen3 and compare it with LLaMAFactory's enable_thinking behavior. The issue names no source file or test; done would require documenting whether datasets without think/\n\n/think tags are supported and how they are processed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100