update llama model

app.py

@@ -78,7 +78,6 @@ print('finished download...')
 # Initialize the Llama model with appropriate settings for GPU
 lcpp_llm = Llama(
     model_path=model_path_llama,
-    n_threads=2,  # CPU cores to use
     n_batch=512,  # Batch size for processing; adjust as per your VRAM capacity
 )
 

llama2_response_mail_generator.py

@@ -2,7 +2,11 @@ from huggingface_hub import hf_hub_download
 
 from llama_cpp import Llama
 
+model_name_or_path = "TheBloke/Llama-2-13B-chat-GGML"
+model_basename = "llama-2-13b-chat.ggmlv3.q5_1.bin"  # The model is in bin format
 
+# Download the model file
+model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename)
 
 # Initialize the Llama model with appropriate settings for GPU
 lcpp_llm = Llama(