Update app.py

app.py

@@ -10,6 +10,7 @@ import requests
 from io import BytesIO
 from unittest.mock import patch
 from transformers.dynamic_module_utils import get_imports
+import os
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)