Stanford CS336: Language Modeling from Scratch
Builds a language model end to end — data, tokenizer, architecture, training, eval, alignment. Lines up with the Raschka book on the bookshelf.
Course site: https://stanford-cs336.github.io/spring2025/.
Plan to start this once I’m further into Build a Large Language Model (From Scratch) — the book gives the implementation, this gives the systems / scaling / data side that the book doesn’t cover.