Update app.py

app.py

@@ -64,8 +64,9 @@ def predict(message, history):
             input_ids=model_inputs,
             streamer=streamer,
             max_new_tokens=1024,
-            do_sample=False)
+            do_sample=False
         )
+        
         t = Thread(target=model.generate, kwargs=generate_kwargs)
         t.start()  # Starting the generation in a separate thread.
         partial_message = ""