适配新版transformers | adapt transformers update (https://github.com/huggingface/transformers/pull/31116)

modeling_chatglm.py

@@ -936,9 +936,18 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
             standardize_cache_format: bool = False,
     ) -> Dict[str, Any]:
         # update past_key_values
-        model_kwargs["past_key_values"] = self._extract_past_from_model_output(
+        past_output = self._extract_past_from_model_output(
             outputs, standardize_cache_format=standardize_cache_format
         )
+        # adapt transformers update (https://github.com/huggingface/transformers/pull/31116)
+        if(type(past_output) is tuple and type(past_output[0]) is str):
+            if past_output[0]=="past_key_values":
+                model_kwargs["past_key_values"] = past_output[1]
+            else:
+                model_kwargs["past_key_values"] = None
+                print(f"WARN: Get \"{past_output[0]}\" during self._extract_past_from_model_output, not \"past_key_values\"")
+        else:
+            model_kwargs["past_key_values"] = past_output
 
         # update attention mask
         if "attention_mask" in model_kwargs: