[Feature request] Visual Question Answering Support

[kevin51jiang]

Name of the feature
In general, the feature you want added should be supported by HuggingFace's transformers library:

• If requesting a model, it must be listed here.
• If requesting a pipeline, it must be listed here.
• If requesting a task, it must be listed here.

• Model: https://huggingface.co/dandelin/vilt-b32-finetuned-vqa
• Pipeline: Visual Question answering

Reason for request
Why is it important that we add this feature? What is your intended use case? Remember, we are more likely to add support for models/pipelines/tasks that are popular (e.g., many downloads), or contain functionality that does not exist (e.g., new input type).

Additional context
Add any other context or screenshots about the feature request here.

[xenova]

Currently, VQA isn't supported in optimum (meaning you can't export ONNX files yet). I will add it once they support it! :)

I've opened a feature request for it here.