diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 81e929aaca..3682c71d7c 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -449,7 +449,7 @@ def patch_trl_rl_trainers(): pass -def PatchFastRL(algorithm = "GRPO", FastLanguageModel = None): +def PatchFastRL(algorithm = None, FastLanguageModel = None): if FastLanguageModel is not None: PatchRL(FastLanguageModel) patch_trl_rl_trainers() if algorithm is not None: PatchRLStatistics(algorithm)