Fix a bug in Qwen2Audio (#32552)

fix _update_model_kwargs_for_generation

src/transformers/models/qwen2_audio/modeling_qwen2_audio.py

@@ -1328,13 +1328,10 @@ class Qwen2AudioForConditionalGeneration(Qwen2AudioPreTrainedModel):
         outputs: ModelOutput,
         model_kwargs: Dict[str, Any],
         is_encoder_decoder: bool = False,
-        standardize_cache_format: bool = False,
         num_new_tokens: int = 1,
     ) -> Dict[str, Any]:
         # update past_key_values keeping its naming used in model code
-        cache_name, cache = self._extract_past_from_model_output(
-            outputs, standardize_cache_format=standardize_cache_format
-        )
+        cache_name, cache = self._extract_past_from_model_output(outputs)
         model_kwargs[cache_name] = cache
         if getattr(outputs, "state", None) is not None:
             model_kwargs["state"] = outputs.state