Replies: 1 comment
-
在对 rec(文本识别)模型进行微调时,关于原始数据和新数据的比例,主要有以下建议:
例如:
总结:如果使用通用数据进行微调,建议保证垂类数据与通用数据比例 1:1;如果是加入特定字符数据进行精调,建议保持原始数据与新增数据比例在 10:1 ~ 5:1 之间,以避免模型过拟合。 Response generated by 🤖 feifei-bot | chatgpt-4o-latest |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
rec模型微调时,原数据要保留多少?新数据要多少?
Beta Was this translation helpful? Give feedback.
All reactions