diff --git a/unsloth/models/rl.py b/unsloth/models/rl.py
index 62141b8700..d5524ff5f5 100644
--- a/unsloth/models/rl.py
+++ b/unsloth/models/rl.py
@@ -1173,30 +1173,33 @@ def patch_functions(RLTrainer, trainer_file, RLTrainer_name, all_imports, import
     # When "ref" is not in peft_config, GRPO/RLOO fallback uses disable_adapter()
     # which gives the base model logits - exactly what we want
     add_adapter_block_pattern = (
-        r'([ \t]*)'  # Capture leading indentation
-        r'if\s+is_peft_available\(\)\s+and\s+is_peft_model\(model\)\s+and\s+args\.beta\s*!=\s*0\.0\s*:'
-        r'(.*?)'  # Match the entire block until ref_param.data.copy_
-        r'ref_param\.data\.copy_\(param\.data\)'
+        r"([ \t]*)"  # Capture leading indentation
+        r"if\s+is_peft_available\(\)\s+and\s+is_peft_model\(model\)\s+and\s+args\.beta\s*!=\s*0\.0\s*:"
+        r"(.*?)"  # Match the entire block until ref_param.data.copy_
+        r"ref_param\.data\.copy_\(param\.data\)"
     )
+
     def comment_out_block(match):
         """Comment out each line in the matched block, preserving indentation."""
         full_match = match.group(0)
         indent = match.group(1)
-        lines = full_match.split('\n')
+        lines = full_match.split("\n")
         commented_lines = []
         # Add explanation comment first
-        commented_lines.append(f"{indent}# Unsloth: Commented out - use base model as reference, not SFT/LoRA model")
+        commented_lines.append(
+            f"{indent}# Unsloth: Commented out - use base model as reference, not SFT/LoRA model"
+        )
         # Comment out each line - insert # after leading whitespace to preserve indentation
         for line in lines:
             if line.strip():
                 stripped = line.lstrip()
-                leading_ws = line[:len(line) - len(stripped)]
+                leading_ws = line[: len(line) - len(stripped)]
                 commented_lines.append(f"{leading_ws}# {stripped}")
             else:
                 commented_lines.append(line)
-        return '\n'.join(commented_lines)
-    init = re.sub(add_adapter_block_pattern, comment_out_block, init, flags=re.DOTALL)
+        return "\n".join(commented_lines)
 
+    init = re.sub(add_adapter_block_pattern, comment_out_block, init, flags = re.DOTALL)
 
     # Set use_vllm if not set
     if "args.use_vllm" in init and "model" in init and "args" in init: