Update app.py

app.py

@@ -5,10 +5,10 @@ import torch
 from threading import Thread
 import os
 
-@spaces.GPU
+@spaces.GPU()
 def load_model(model_name):
     return pipeline("text-generation", model=model_name, device_map="cuda", torch_dtype=torch.bfloat16, trust_remote_code=True, token=os.environ["token"], use_fast=True)
-@spaces.GPU()
+@spaces.GPU(duration=120)
 def generate(
     message,
     history,