Update app.py

app.py

@@ -2,6 +2,9 @@ import torch
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
 
+
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+
 # Initialize Florence model
 device = "cuda" if torch.cuda.is_available() else "cpu"
 florence_model = AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True).to(device).eval()