Updating the model

Updating the model following the base model update (now needs transforemrs>=4.44.0), check https://github.com/THUDM/GLM-4/blob/main/basic_demo/requirements.txt for updated requirement

config.json

@@ -38,7 +38,7 @@
   "seq_length": 131072,
   "use_cache": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.44.0",
   "tie_word_embeddings": false,
   "eos_token_id": [151329, 151336, 151338],
   "pad_token_id": 151329

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.8,
   "max_length": 128000,
   "top_p": 0.8,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.44.0"
 }

modeling_chatglm.py

@@ -924,12 +924,9 @@ 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