Update app.py

app.py

@@ -2,10 +2,12 @@ from llama_cpp.server.app import create_app, Settings
 from fastapi.responses import HTMLResponse
 import os
 
+urlretrieve("https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GGUF/resolve/main/openhermes-2-mistral-7b.Q4_0.gguf", "./model.gguf")
+
 app = create_app(
     Settings(
         n_threads=2,  # set to number of cpu cores
-        model="https://huggingface.co/TheBloke/OpenHermes-2-Mistral-7B-GGUF/resolve/main/openhermes-2-mistral-7b.Q4_0.gguf",
+        model="./model.gguf",
         embedding=False
     )
 )