Update app.py

app.py

@@ -56,7 +56,7 @@ class GradioTextStreamer(TextStreamer):
                 self.text_queue.get_nowait()
             except queue.Empty:
                 break
-
+@spaces.GPU()
 def generate_response(message, history, max_tokens, temperature, top_p):
     """Generate streaming response"""
     global model, tokenizer