We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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?
{"query": str, "pos": List[str], "neg":List[str], "pos_scores": List[int], "neg_scores": List[int], "prompt": str}
prompt
pos_scores,neg_scores
The text was updated successfully, but these errors were encountered:
No branches or pull requests
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?The text was updated successfully, but these errors were encountered: