diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py
index ff9bc1ec78..ea7183fc5a 100644
--- a/unsloth/models/rl_replacements.py
+++ b/unsloth/models/rl_replacements.py
@@ -215,13 +215,19 @@ def grpo_trainer__generate_and_score_completions(function_name, function):
     # The new multi-line string that will replace the line above
     replacement_lines = """
         batch_size = self.args.per_device_train_batch_size if mode == "train" else self.args.per_device_eval_batch_size
-        if not has_images:
-            # Left pad prompt before calculation old and ref hidden states
-            prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
-        self.model.for_training()"""
+        try:
+            #TRL 0.23.1 and below path
+            if not has_images:
+                # Left pad prompt before calculation old and ref hidden states
+                prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
+            self.model.for_training()
+        except: 
+            #TRL 0.24.0 and below path
+            if images is None:
+                # Left pad prompt before calculation old and ref hidden states
+                prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
+            self.model.for_training()"""
 
-    if "has_images" not in function:
-        raise NotImplementedError("Unsloth: For now we support `trl<=0.23.1`. Please downgrade!")
     function = function.replace(line_to_replace, replacement_lines)
 
     pattern_to_find = re.compile(