Florence 2 support :)

Open SinanAkkoyun opened this issue 1 year ago • 2 comments

Motivation

Hey! I am currently struggling to get Florence 2 running in a VRAM efficient batched way. Having easy and scalable API access would be very awesome if it's not too much work!

Thank you very much ^^

Related resources

No response

Additional context

No response

Jul 16 '24 22:07 SinanAkkoyun

ref https://github.com/InternLM/lmdeploy/blob/main/docs/en/advance/pytorch_new_model.md https://huggingface.co/collections/microsoft/florence-6669f44df0d87d9c3bfb76de

Jul 17 '24 02:07 zhyncs

Is there any plan to implement florence2 into this project? @lvhan028

Sep 05 '24 08:09 davertor