[Multi-Adapter PPO] Fix and Refactor reward model adapter #982

Merged

younesbelkada merged 4 commits intohuggingface:mainfrom mnoukhov:reward-model-adapter

Nov 21, 2023

+102-83

Commits on Nov 10, 2023

Commits on Nov 20, 2023

change supported_args back to None
mnoukhov
committed