Modelpublic

imminsik/safe-rlhf-qr-verbosity-alpaca-8b-reproduced-llama-3

sourceHugging Faceupdated 9mo agoView on Hugging Face

0likes6downloads

2 commits on main

01023269mo ago

Upload verbosity quantile regression reward model

imminsik

d238c889mo ago

initial commit

imminsik