Update app.py

app.py

@@ -1,5 +1,5 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
-device = "cuda" # the device to load the model onto
+device = "cpu" # the device to load the model onto
 
 model = AutoModelForCausalLM.from_pretrained(
     "NTQAI/Nxcode-CQ-7B-orpo",