IV — What Makes an LLM → Chapter 16
FROM SYSTEMS TO FRONTIER ML

Pretraining

Next-token prediction, the data pipeline, scaling laws (Chinchilla), what a 'token budget' is.

§1 Pretraining — next-token prediction at trillion-token scale §2 The data pipeline — Common Crawl to training tokens §3 Chinchilla scaling laws — the compute-optimal frontier

← ALL CHAPTERS