Update app.py

app.py

@@ -8,7 +8,7 @@ import os
 @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(duration=120)
+@spaces.GPU(duration=45)
 def generate(
     message,
     history,