Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import torch
+import spaces
 from transformers import pipeline
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
@@ -8,6 +9,8 @@ device = 'cuda' if torch.cuda.is_available() else 'cpu'
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
 
+
+@spaces.GPU(duration=120)
 def respond(
     message,
     history: list[tuple[str, str]],