diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py index 5d2270810c..914d403f6b 100644 --- a/unsloth/models/rl.py +++ b/unsloth/models/rl.py @@ -440,6 +440,9 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"): "torch_empty_cache_steps" : 250, "logging_steps" : 1, "max_seq_length" : None, + "num_generations" : 8, + "top_k" : None, + "vllm_mode" : "colocate", } for k, v in replacements.items(): x = f"{k}( = [^,\n]{{1,}})?,\n"