Update app.py

app.py

@@ -10,7 +10,7 @@ print("CUDA version:", torch.version.cuda)
 # Load the Hugging Face token from secrets
 token = os.environ.get("HF_TOKEN")
 
-model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+model_id = "google/shieldgemma-2b"
 
 # use quantization to lower GPU usage
 bnb_config = BitsAndBytesConfig(