mirror of
https://github.com/huggingface/trl.git
synced 2025-10-20 18:43:52 +08:00
* adds a more fine grained profiling context * precommit * fix reward func name * add reward to RM name * Update trl/extras/profiling.py Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> * some doc and fixes --------- Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com> Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>
152 B
152 B