Update app.py

app.py

@@ -92,7 +92,7 @@ def apply_llama3_chat_template(conversation, add_generation_prompt=True):
         prompt += "<|ASSISTANT|>\n"
     return prompt
 
-@spaces.GPU(duration=120)
+@spaces.GPU()
 def generate_response(message, chat_history, system_prompt, temperature, max_tokens, top_p, top_k, repetition_penalty):
     # Build the conversation history.
     conversation = [{"role": "system", "content": system_prompt}]