Update app.py

app.py

@@ -10,6 +10,9 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=dtype,
     device_map="auto",
 )
+# Use GPU if available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
 
 preamble = "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."