Update app.py

app.py

@@ -10,11 +10,7 @@ model_name = "meta-llama/Meta-Llama-3-8B-Instruct"
 hf_token = os.environ.get("HF_TOKEN")
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    quantization_config=bnb_config,
-    use_auth_token=hf_token
-)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_token)
 model.to("cpu")  # move model to CPU (if not using GPU Space)
 
 # Prompt generator