Update app.py

app.py

@@ -14,14 +14,14 @@ import gradio as gr
 
 
 # Enable flash attention
-subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+# subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
 # Load the visual document retrieval model (ColQwen2)
 model = ColQwen2.from_pretrained(
     "vidore/colqwen2-v1.0",
     torch_dtype=torch.bfloat16,
     device_map="cuda:0",
-    attn_implementation="flash_attention_2",
+    # attn_implementation="flash_attention_2",
 ).eval()
 processor = ColQwen2Processor.from_pretrained("vidore/colqwen2-v1.0")