Inference problem about the demo.

[ApolloRay]

I want to reproduce the same result as the demo.
I download image and use the same question ("Explain why this meme is funny, and generate a picture when the weekend coming.") , model generate the wrong answer.

For evaluation, I use the model_vqa script. I rewrite the qs and image_file_path.
I'm not sure where is the problem.

[ApolloRay]

I change the conv_mode from llava_v1 to chatml_direct. It works, but I can't get the same result as the official demo.