add llama_model directory

app.py

@@ -73,7 +73,7 @@ model_basename = "llama-2-13b-chat.ggmlv3.q5_1.bin"  # The model is in bin forma
 
 # Download the model file
 print('downloading llama model...')
-model_path_llama = hf_hub_download(repo_id=model_name_or_path, filename=model_basename, force_download=True)
+model_path_llama = hf_hub_download(repo_id=model_name_or_path, filename=model_basename, force_download=True, local_dir="./llama-model")
 print('finished download...')
 # Initialize the Llama model with appropriate settings for GPU
 lcpp_llm = Llama(