Update app.py

app.py

@@ -27,7 +27,7 @@ MAX_MAX_NEW_TOKENS = 6144
 DEFAULT_MAX_NEW_TOKENS = 6144
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "6144"))
 
-device = torch.device("auto" if torch.cuda.is_available() else "cpu")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 #model_id = "nltpt/Llama-3.2-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id,token=access_token)