Vision language model support

[merveenoyan]

Hello! 💗 When trying to run benchmarks on vision language models (image-text-to-text) I realized this library doesn't support this task. It would be nice to have a support for it since these models are almost as mainstream as LLMs.

[IlyasMoutawwakil]

Hi, done in #296 🤗 I remember giving you my word so had to do it 🔥
I also added a small config for testing so that we can iterate and test it.