BBC-Esq

That Netron is awesome, thanks. It worked for most of the models and I was automatically directed to their github where I submitted an issue. Overall, it loaded all of...

> Can you provide a minimal code using just huggingface transformers and sentence-transformers? What does it take to run forward passes with them? > > The instructor models and the...

I just tried to do this PR but don't know what I'm doing at all...please help. I noticed that you've done converters before. https://github.com/OpenNMT/CTranslate2/pull/1639

BTW, I think that sentence transformers just started supporting instructor models recently!!! https://www.sbert.net/docs/pretrained_models.html#instructor-models

But "reportedly" they're only supported up to ```sentence-transformers 2.2.2```, but I haven't had a chance to test this yet... https://github.com/UKPLab/sentence-transformers/issues/2474#issuecomment-1930707429

I finally resolved it myself but haven't had a chance to upload the script to any fork of any repo.

Here's the modified script. Let me know if it works for you as I'd appreciate the shout out. ;-) name the script "instructor" and replace the "instructor.py" script in the...

Also, I'm stuck on using sentence-transformers==2.2.2 because, reportedly, anything after that doesn't work with the Instructor models, which I love so...And you use ==2.5.0 so...Now apparently I have to choose...

Already been looking at it..might be too daunting for me. Is better transformer relatively easy though? Is the snippet you gave me for my script?

> RAM Usage: Depends on batch_size mostly - int8 is hard - check out my quantization code. Might not lead to a lot of speedups or memory usage yet. Would...