change to Llama-3.3-70B-Instruct

app.py

@@ -61,7 +61,7 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 print(f"Using device: {device}")
 # Load models once
 print("Loading models...")
-model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+model_id = "meta-llama/Llama-3.3-70B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,