CoolFace
Modelpublic

anirudhb11/critic_200_ppo-run-math-training-prompt-len-800-response-len-4096-r3-actor-low-lr-0-ae0cd033d2

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes4downloads
4 commits on main
4bbed0d1y ago

Add metadata

anirudhb11
0a756a21y ago

Add tokenizer

anirudhb11
18f1aa61y ago

Push critic checkpoint

anirudhb11
722a4ee1y ago

initial commit

anirudhb11