diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 24a5c8d1f..1639590c2 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -401,6 +401,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): RLTrainer_source, f"trl.trainer.{trainer_file}", imports, + overwrite = False, ) # Patch Trainer