Looking for experts for doing a Hateful Meme Detection Project

I’m a undergraduate trying to a NLP project on Hateful Meme Detection. I’m referencing this paper. I would like to know whether there are anyone who would be willing to help in building a simpler model based on the same architecture. The original codebase in the paper is too complicated for me and training the images would be costly and resource intensive.

The above is architecture model based on the original paper.

Would like to know any online resources that I can refer to know more about this topic.

Thanks very much for your time! Sorry in advance, if this is not the right forum for this kind of question.
P.S: I’m willing to pay for the project.