Update app.py

app.py

@@ -18,14 +18,14 @@ def install_fa2():
     print("Install FA2")
     os.system("pip install flash-attn --no-build-isolation")
 
-install_fa2()
+# install_fa2()
 
 
 model = ColQwen2.from_pretrained(
         "vidore/colqwen2-v1.0",
         torch_dtype=torch.bfloat16,
         device_map="cuda:0",  # or "mps" if on Apple Silicon
-        attn_implementation="flash_attention_2", # should work on A100
+        # attn_implementation="flash_attention_2"
     ).eval()
 processor = ColQwen2Processor.from_pretrained("vidore/colqwen2-v1.0")