modelscope / modelscope/ms-swift
请问基于token的加权怎么在数据集中设置
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
文档中定制化loss_scale部分提到，loss_scale可以让开发者自由地定义自己的token权重。请问这个权重参数在哪里设置？有参考数据集标注示例吗？谢谢！
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
Start with the documentation's customized loss_scale section and compare its explanation with the linked screenshot. Done means documenting where token weights are configured and adding a reference dataset-annotation example, if supported.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100