Upload 2 files

app.py

@@ -5,8 +5,11 @@
 import gradio as gr
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
-import torch
 import numpy as np
+import spaces
+
+import subprocess
+subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 # Cargar modelo y procesador
 ocr_model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)

requirements.txt

@@ -3,6 +3,5 @@ Pillow
 torch
 numpy
 transformers
-flash_attn 
-einops 
-timm
+timm
+spaces