modelscope / modelscope/ms-swift
qwen3-embedding模型微调时,loss用infonce,positive_messages支持多个吗
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
数据集格式提到positive_images外层只有一个,但是评测那里又提到"mean_pos 所有positive的平均值"
如果不支持,自行修改loss部分的源码,其他代码地方还会有问题不?
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
No files or tests are named. Start by tracing the dataset handling for positive_images and positive_messages, then inspect the InfoNCE loss entry point and the evaluation calculation for mean_pos. Done means determining whether multiple positive messages are supported and identifying all affected paths if the loss behavior is changed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100