CoolFace
Modelpublic

Xiaolihai/etd-policy-rl-only-judgment

sourceHugging Faceupdated 15d agoView on Hugging Face
0likes19downloads
2 commits on main
e186afa15d ago

EtD DPO judgment adapter (9437 pairs, beta=0.1, epochs=1.0)

Xiaolihai
560969e15d ago

initial commit

Xiaolihai