Update app.py

app.py

@@ -8,6 +8,8 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 model.eval()
 
+model = torch.compile(model)
+
 if torch.cuda.is_available():
     model = model.to("cuda")