How do you implement SLic on pair_pm model?

[t-sifanwu]

Hi, thanks for uploading the code for pair_pm! Since in the blog, it seems that you are using SLiC for pair_pm models. In the directory of pair_pm, I can't find the code for using slic methods.

[WeiXiongUST]

Hi, thanks for your interest in our project!

We mention Slic paper because the pair-wise model training was first proposed in this paper. We do not do RLHF in this project. If you are interested in the subsequent RLHF stage, you may check this project https://github.com/RLHFlow/Online-RLHF