delete the limit of max_new_token

app.py

@@ -83,7 +83,7 @@ def query_model(user_input, history):
     messages = [{"role": "user", "content": combined_query}]
     
     response = ""
-    for new_text in chat_model.stream_chat(messages, max_new_tokens=512, temperature=0.9):
+    for new_text in chat_model.stream_chat(messages, temperature=0.9):
         response += new_text
         yield response