modelscope / modelscope/ms-swift
rlhf rm训练时，如果初始model不存在value_head，得到的模型似乎也没有保存value_head？
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
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
The report only identifies RLHF reward-model training and includes an image; no source file or test is named. Start by reproducing training with an initial model that lacks a value_head, then inspect the saved model structure. Done means determining whether value_head should be saved and correcting or documenting the observed behavior.
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
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100