[Feature Request] Support instructor-xl (for text embeddings)

[sroussey]

It ranks at the top in the hugging-face leaderboard:

https://huggingface.co/spaces/mteb/leaderboard

Here is more info:

https://huggingface.co/hkunlp/instructor-xl

It is a little different... you add an instruction context separately from the thing you want to create embeddings. Quite versatile; obviates the need for many specialized models.

[skeskinen]

It's not instructor-xl, but I've done ggml implementation of BERT for sentence embeddings here: https://github.com/skeskinen/bert.cpp

[ggerganov]

@skeskinen

Really well done! Feel free to add a link to your project in ggml’s README
Adding batching support to ggml is getting higher on the TODO list. Now with bert.cpp we’ll have something to easily test with!

[skeskinen]

Thanks! Adding support for batching sounds exiting 👍
It'll be nice to see what kind of speedup it will give and if bert.cpp will be faster than pytorch(cpu) in batched head to head.