Add support for EVA-CLIP model

[stoensin]

Dear developers,

I would like to request the addition of support for the EVA-CLIP model in this project. EVA-CLIP is a powerful image-text dual-encoder model that has shown strong performance on a variety of visual tasks.

Including support for EVA-CLIP would be valuable for users who wish to leverage its capabilities for their own applications and research. The ability to easily integrate EVA-CLIP into this project would greatly expand its utility and functionality.

I would be happy to contribute to the development effort required to implement EVA-CLIP support, if that would be helpful. Please let me know if you have any questions or need further information from me.

Thank you for your consideration.
eva-clip:https://github.com/baaivision/EVA/tree/master/EVA-CLIP
Best regards
🤩

[AlekseySh]

Hi,

Thank you for your interest!

Does EVA-CLIP have any requirements different from what we have in OML? (You could check them in the ci folder of the repo).

Here is the recent PR where we added DINO v2 model. Just for reference.
PR

[AlekseySh]

Deu to inactivity