Update main.py

main.py

@@ -2,12 +2,15 @@ from fastapi import FastAPI
 from pydantic import BaseModel, Field
 from typing import List, Dict
 from llama_cpp import Llama
+import os
+os.environ["HF_HOME"] = "./cache"
 
 # Load the Llama model with the specified path and configuration
 llm = Llama.from_pretrained(
     repo_id="bartowski/Llama-3.2-3B-Instruct-GGUF",  # Replace with the actual model repository ID
     filename="Llama-3.2-3B-Instruct-Q8_0.gguf",      # Replace with your actual model filename if necessary
     n_ctx=4096,
+    cache_dir="./cache",
     n_threads=2,
 )