Add zero-shot classification task for BLIP-2

### Feature request I would like to add the support for the zero-shot classification task using BLIP2, computing text-image similarities with the normalized embeddings, that would be accessed from BLIP2 feature extractor. The idea is to enable calling the zero-shot classification pipeline using BLIP2, by implementing the `get_image_feature`and `get_text_features`methods. I would love more guidance, if possible, on the criteria for accepting the PR. ### Motivation This is related to the following the discussion on this issue on the hub, and the comment left by @NielsRogge here https://huggingface.co/Salesforce/blip2-opt-2.7b/discussions/3#64cbe5e487ec96aa473a1f54 . ### Your contribution I would like to submit a PR to contribute for this feature.