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.

Sign up for GitHub

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

Jump to bottom

Wombat与RRHF #40

Open

Guochry opened this issue Aug 2, 2023 · 4 comments

Guochry commented Aug 2, 2023

想请问一下，有比较不同reward来源的实验吗？即比较“开源reward model”和“ChatGPT”分别作为reward score来源的效果孰优孰劣吗？

Owner

GanjinZero commented Aug 2, 2023

没有做过开源rm的；我们做的时候没有什么好的开源rm

Author

Guochry commented Aug 3, 2023

请问Dahoas/gptj-rm-static不是吗）

Owner

GanjinZero commented Aug 3, 2023

只能在hh上用，而且准确性不高

Author

Guochry commented Aug 3, 2023

好吧，谢谢您啦

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment