CoolFace
Modelpublic

wuschelschulz/gemma_1_reasoning_reward_hacking_SFT_debug

sourceHugging Faceupdated 9mo agoView on Hugging Face
0likes
discussions and pull requests

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.

Open discussions on Hugging Face
wuschelschulz/gemma_1_reasoning_reward_hacking_SFT_debug · CoolFace