diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index fadae874db..048ec7bb02 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -566,8 +566,8 @@ pass def PatchFastRL(algorithm = None, FastLanguageModel = None): - return - # if FastLanguageModel is not None: PatchRL(FastLanguageModel) - # patch_trl_rl_trainers() - # if algorithm is not None: PatchRLStatistics(algorithm) + if FastLanguageModel is not None: PatchRL(FastLanguageModel) + patch_trl_rl_trainers() + if type(algorithm) is str and algorithm.islower(): + PatchRLStatistics(algorithm) pass