modelscope / modelscope/ms-swift
Gemma 4 Using Audio + (Video or Image) for SFT, the code does not work or run at the START
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
Checklist / 检查清单
- I have searched existing issues, and this is a new bug report. / 我已经搜索过现有的 issues，确认这是一个新的 bug report。
Bug Description / Bug 描述
When using gemma4 for embedding model sft. we do work at either of below 3 situations:
- Only using Audio data as INPUT
- Only using Image data as INPUT
- Only using Video data as INPUT
But, When we mix audio with either (Image or Video), the training code do not run at START:
Hope some suggestions!
How to Reproduce / 如何复现
Default env
Additional Information / 补充信息
No response
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 by reproducing the failure in the default environment with Gemma 4 SFT using audio combined with image or video, then compare it with the working single-modality cases. Done means the mixed audio-plus-image or audio-plus-video training code starts successfully; the issue does not identify a file, test, traceback, or exact command.
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