From bef0371cc668f48c0cbc8dd3a629b05dae6754d5 Mon Sep 17 00:00:00 2001 From: numb3r33 Date: Sat, 20 Dec 2025 12:30:33 +0530 Subject: [PATCH] Remove the comment. --- unsloth/models/rl_replacements.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index dd139ffd25..248c5aab85 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -390,7 +390,7 @@ def grpo_trainer__generate_and_score_completions(function_name, function): function = patched function = function.replace( - " return output", # 8 spaces before 'return' + " return output", """ if not _was_training: self.model.for_inference() return output"""