Change default max length

modeling_chatglm.py

@@ -935,7 +935,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
 
 
     @torch.no_grad()
-    def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 2048, num_beams=1,
+    def chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, max_length: int = 8192, num_beams=1,
              do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None, **kwargs):
         if history is None:
             history = []
@@ -954,7 +954,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
 
     @torch.no_grad()
     def stream_chat(self, tokenizer, query: str, history: List[Tuple[str, str]] = None, past_key_values=None,
-                    max_length: int = 2048, do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None,
+                    max_length: int = 8192, do_sample=True, top_p=0.8, temperature=0.8, logits_processor=None,
                     return_past_key_values=False, **kwargs):
         if history is None:
             history = []