Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

bge-reranker-v2-m3微调文本相似度,训练数据格式问题 #1382

Open
adatwfx opened this issue Feb 26, 2025 · 0 comments
Open

bge-reranker-v2-m3微调文本相似度,训练数据格式问题 #1382

adatwfx opened this issue Feb 26, 2025 · 0 comments

Comments

@adatwfx
Copy link

adatwfx commented Feb 26, 2025

finetune页面 给出的训练数据格式为
{"query": str, "pos": List[str], "neg":List[str], "pos_scores": List[int], "neg_scores": List[int], "prompt": str}
请问针对特定领域文本相似度的微调,prompt应该怎么设置?pos_scores,neg_scores是必须提供的吗?负例数量控制在多少个合适?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant