Update app.py

app.py

@@ -18,7 +18,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     quantization_config=nf4_config,
-    device_map="cpu"
+    device_map="auto"
 )
 
 model.tie_weights()