diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index a56a7840cc..e8fb1ffc08 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -168,11 +168,12 @@ def grpo_trainer__get_per_token_logps(function_name, function): ) if len(original) != 0: original = original[0] + spaces = function.find(original) replacer = \ "with torch.amp.autocast(device_type = 'cuda', "\ "dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16) "\ "if not torch.is_autocast_enabled('cuda') else nullcontext():\n" + \ - " "*8 + original + " "*(spaces + 4) + original function = function.replace(original, replacer) pass return function