CoolFace
Modelpublic

Akahsizrr/AIAAH-1-RL-DPO-iter1

sourceHugging Faceapache-2.0updated 12d agoView on Hugging Face
2likes83downloads
2 commits on main
d41dec212d ago

AIAAH-1 RL-DPO iter1: coding 80->90%, math 93->97%, combined +6.7%

Akahsizrr
6395a5d12d ago

initial commit

Akahsizrr