feat: stream block ended with newline

modeling_chatglm.py

@@ -1313,7 +1313,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
             response = tokenizer.decode(outputs)
             response = self.process_response(response)
             new_history = history + [(query, response)]
-            yield response, new_history
+            yield response + "\n", new_history
 
     @torch.no_grad()
     def stream_generate(