Add support for BLIP-2 multimodal feature extraction

[youssefadr]

What does this PR do?

This PR introduces the addition of get_image_feature and get_text_feature methods to the Blip2ForConditionalGeneration class. These changes align with the original Qformer implementation, which utilized both text and image inputs.

The current implementation in HuggingFace lacks support for multimodal embeddings, especially the capacity to extract embeddings by passing both text and image to the QFormer. This PR addresses this shortcoming.

Fixes #25300 #25245

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint.

[sgugger]

cc @amyeroberts and @younesbelkada

[younesbelkada]

Awesome work @youssefadr ! let us know when the PR is ready for review

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[ArthurZucker]

Hey @youssefadr, feel free to re-open this if you still plan on adding this feature

[youssefadr]

@ArthurZucker Thank you, I'll do it, I am sorry I couldn't find time lately for it. It is on my backlog!

[youssefadr]

@NielsRogge Hi, should I open a new PR for this, or is there a way to re-open this one? It seems to be requested by a lot of users.

[ajpuyle]

Is this still being worked on? I am in need of this tool.

[ArthurZucker]

it's stale, feel free to take it over