Ethan Yanjia Li
Results
22
comments of
Ethan Yanjia Li
@zhisbug Yes. that would be great. Zhuohan has my wechat.
@infwinston I used https://huggingface.co/datasets/Anthropic/hh-rlhf dataset when I do the RLHF in my project here: https://github.com/ethanyanjiali/minChatGPT I guess you can take the harmfulness part of this dataset to evaluate. That paper...