diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 1aacade93d..24f503dc6a 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -481,7 +481,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): RLTrainer_source, f"trl.trainer.{trainer_file}", imports, - overwrite = False, + overwrite = True, ) # Patch Trainer