Update app.py

app.py

@@ -15,6 +15,7 @@ if torch.cuda.is_available():
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
+@spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],