Viewing profile — xzyaoi

Do you usually do full fine-tuning or LoRA (or its variants)? and why?

There's also papers for hosting full-parameter fine-tuned models: https://arxiv.org/abs/2312.05215 Disclaimer: I'm one of the authors.

https://github.com/autoai-org/aid I choose YouTube link as I felt it describes better, hopefully:(

Awesome!

It's here. https://docs.rsshub.app/en/ By the way, I've been using this for a while and it is superb.

It would be great if they could explain this decision in more detail, but I guess they are still working on to explain this better and clearer.

What specific level have you already achieved? Are you looking for optimizations, manifolds or something else?

https://github.com/autoai-org/CVPM

Documents： https://cvpm.autoai.org/ GitHub: https://github.com/unarxiv/cvpm 中文介绍(Chinese Intro): https://zhuanlan.zhihu.com/p/45672318 CVPM (Computer Vision Package Manager) is an …