Update app.py

app.py

@@ -1,9 +1,10 @@
+import os
 from threading import Thread
 from typing import Iterator
+
 import gradio as gr
 import spaces
 import torch
-import os
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
 MAX_MAX_NEW_TOKENS = 2048
@@ -26,6 +27,7 @@ LICENSE = """<p/> ---."""
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU  This demo does not work on CPU.</p>"
 
+@spaces.GPU(duration=120)
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],