Update app.py

app.py

@@ -8,7 +8,8 @@ model = AutoModel.from_pretrained(
     'OpenGVLab/InternViT-6B-448px-V1-5',
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
-    trust_remote_code=True
+    trust_remote_code=True,
+    use_flash_attn=False  # Disable Flash Attention
 ).cuda().eval()
 
 # Load the image processor