diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index e8d9c19a54..2342574737 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -387,6 +387,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): f"class {RLTrainer_name}", f"class Unsloth{RLTrainer_name}", 1 ) exec(RLTrainer_source, imported_functions, globals()) + globals()[f"Unsloth{RLTrainer_name}"] = eval(f"Unsloth{RLTrainer_name}") exec(f"trl.trainer.{trainer_file}.{RLTrainer_name} = Unsloth{RLTrainer_name}", locals(), globals()) exec(f"trl.trainer.{RLTrainer_name} = Unsloth{RLTrainer_name}", locals(), globals()) exec(f"trl.{RLTrainer_name} = Unsloth{RLTrainer_name}", locals(), globals())