Update app.py

app.py

@@ -60,7 +60,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, token= token,
 
 # Load the model with the inferred device map
 # model = load_checkpoint_and_dispatch(model, model_id, device_map=device_map, no_split_module_classes=["GPTJBlock"])
-# model.half()
+model.half()