Update app.py

app.py

@@ -1,3 +1,7 @@
+import subprocess
+# Installing flash_attn
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 import gradio as gr
 from PIL import Image 
 from transformers import AutoModelForCausalLM