WARM: On the Benefits of Weight Averaged Reward Models

Open Webpage

Alexandre Ramé, Nino Vieillard, Léonard Hussenot, Robert Dadashi, Geoffrey Cideron, Olivier Bachem, Johan Ferret

Published: 01 Jan 2024, Last Modified: 30 Sept 2024ICML 2024EveryoneRevisionsBibTeXCC BY-SA 4.0