RegularizedSelfPlay/Llama-3-8B-Instruct-SPPO-Iter2-gp-8b-gpm-reg0.05-sppo-reversekl-table

Conversations for this repository live on Hugging Face.

CoolFace shows imported repositories read-only. Posting into someone else’s repository from here would need an authorised integration and the account holder’s consent, so the link goes to the source instead.