Upload 7 files

generation_config.json

@@ -1,13 +1,13 @@
 {
-  "do_sample": true,
   "eos_token_id": [
     151329,
     151336,
     151338
   ],
-  "max_length": 8192,
   "pad_token_id": 151329,
+  "do_sample": true,
   "temperature": 0.8,
+  "max_length": 8192,
   "top_p": 0.8,
-  "transformers_version": "4.43.1"
-}
+  "transformers_version": "4.44.0"
+}

modeling_chatglm.py

@@ -1082,12 +1082,9 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
             outputs: ModelOutput,
             model_kwargs: Dict[str, Any],
             is_encoder_decoder: bool = False,
-            standardize_cache_format: bool = False,
     ) -> Dict[str, Any]:
         # update past_key_values
-        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
 
         # update attention mask
@@ -1329,4 +1326,4 @@ class ChatGLMForSequenceClassification(ChatGLMPreTrainedModel):
             past_key_values=transformer_outputs.past_key_values,
             hidden_states=transformer_outputs.hidden_states,
             attentions=transformer_outputs.attentions,
-        )
+        )