I have a mix of machine learning guides and tools here.
A substantial part of this repository is dedicated to a brain dump of my experiences training Large Language Models (LLM). e.g., a lot of the know-how I acquired while training the first open-source BLOOM-176B model in 2022. Currently I'm working on a largish multi-modal training so gradually I've been expanding my knowledge.
In this repo you will find various very useful tools in my toolbox (mainly Machine Learning). You're welcome to use them in your work.
Every tool comes with either its own instructional .md file with or the usage is documented at the top of the script.
Continued on my other repos:
If you found a bug, typo or would like to propose an improvement please don't hesitate to open an Issue or contribute a PR.