Ask HN: How do you fine-tune LLMs?
Do you usually do full fine-tuning or LoRA (or its variants)? and why?
Do you usually do full fine-tuning or LoRA (or its variants)? and why?
Disclaimer: I'm one of the authors.
I choose YouTube link as I felt it describes better, hopefully:(
By the way, I've been using this for a while and it is superb.
Documents: https://cvpm.autoai.org/GitHub: https://github.com/unarxiv/cvpm中文介绍(Chinese Intro): https://zhuanlan.zhihu.com/p/45672318CVPM (Computer Vision Package Manager) is an open source software to help developers download, install and run computer vision services. It is the 'pip' for computer vision.Though it is still in a very early stage and not recommend for use in production (actually,...