Update app.py

app.py

@@ -4,6 +4,12 @@ from PIL import Image
 import os
 import torch
 from transformers import AutoModelForCausalLM, AutoProcessor
+import subprocess
+from io import BytesIO
+
+# Install flash-attn
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 
 # Load the model and processor
 model_id = "microsoft/Phi-3.5-vision-instruct"