modelscope / modelscope/ms-swift
MiDasheng grpo:expected scalar type Float but found BFloat16
Open
Nobody has claimed this yet.
question
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
Checklist / 检查清单
- I have searched existing issues, and this is a new question or discussion topic. / 我已经搜索过现有的 issues，确认这是一个新的问题与讨论。
Question Description / 问题描述
我们在使用MiDasheng模型进行grpo训练的时候一直会遇到 expected scalar type Float but found BFloat16的报错，换成qwvnvl模型就不会出现这个问题，这个该如何解决呢
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 expected scalar type Float versus BFloat16 traceback in the attached screenshots and reproduce it in MiDasheng GRPO training. Compare the failing path with the Qwen-VL configuration, then identify the affected component and verify that training completes without the dtype error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100