About the finetuned support of the CLIP modal on retrieval task

[Pefect96]

I just want to know if the LAVIS support to finetune the CLIP modal for retrieval task, such as coco or flickr30k dataset? I see that there is nothing about the finetuned support of the pretrained CLIP modal.

If not, Will LAVIS support it in the future version?

Thank you and kind regards.