Update app.py

app.py

@@ -14,7 +14,7 @@ def streaming_respond(question, history):
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
-        max_new_tokens=10,
+        max_new_tokens=250,
         num_beams=1,
     )
     t = Thread(target=model.generate, kwargs=generate_kwargs)