diff --git a/modelscope/models/nlp/qwen/tokenization.py b/modelscope/models/nlp/qwen/tokenization.py
index 459ceaf3..f8f27654 100644
--- a/modelscope/models/nlp/qwen/tokenization.py
+++ b/modelscope/models/nlp/qwen/tokenization.py
@@ -150,7 +150,7 @@ class QWenTokenizer(PreTrainedTokenizer):
                 format(len(ids), self.max_len))
         return ids
 
-    def save_vocabulary(self, save_directory: str) -> Tuple[str]:
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
         """
         Save only the vocabulary of the tokenizer (vocabulary + added tokens).