Hugging Face's free course on large language models and NLP with the Transformers, Datasets and Tokenizers libraries.
Written by the people who build the Hugging Face libraries, this course explains how transformer models work and how to use, fine-tune and share them — from tokenisation and datasets to training and evaluation — using the open-source ecosystem.
glitchdata links to this course; its content, schedule and pricing are set by Hugging Face.
This course is run by Hugging Face. glitchdata describes it and links to it, but doesn't host its lessons — you take it on their site, under their terms.
huggingface.co ↗2 min read
2 min read
2 min read
2 min read
From a promising demo to something you can operate: scope, evaluation, interface and rollout.
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.
How LLM agents call tools in a loop, how to design tools they use well, and how to keep agents safe and reliable.