Server Deployment

main.py

@@ -1,6 +1,8 @@
 from flask import Flask, request, jsonify
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
+from model import model_download
+model_download()
 
 # Initialize the Llama model with chat format set to "llama-2"
 llm = Llama(model_path="./llama-2-7b-chat.Q2_K.gguf", chat_format="llama-2")

model.py

@@ -10,12 +10,10 @@ filename = 'llama-2-7b-chat.Q2_K.gguf'
 # If not provided, the default cache directory will be used
 cache_dir = './path_to_cache_directory'
 
-# Download the file
-file_path = hf_hub_download(
+def model_download():
+    # Download the file
+    file_path = hf_hub_download(
     repo_id=repo_id,
     filename=filename,
-    cache_dir=cache_dir
-)
-
-# The file_path variable now contains the local path to the downloaded file
-print(f"File downloaded to: {file_path}")
+    cache_dir=cache_dir)   # The file_path variable now contains the local path to the downloaded file
+    print(f"File downloaded to: {file_path}")