LLM Library

The LLM Library is a collection of pre-trained language models in printed, hardbound book form. Each volume contains n-gram frequency tables typeset from classic works of literature — the same statistical patterns that underpin modern LLMs, but at human scale. You can hold the entire model in your hands and use it to generate new text with pen, paper, and dice.

The distinctive feature is the curation. Each volume is built from a specific classic work (or collected works of an author) chosen for its literary character, then typeset in bigram, trigram, and 4-gram variants. The progression across volumes demonstrates the fundamental trade-off between model size and output quality — a trigram model of Frankenstein produces noticeably more coherent text than the bigram version, but the book is considerably thicker.

Current volumes include Mary Shelley’s Frankenstein, Tim Winton’s Cloudstreet, the collected works of Ernest Hemingway, and a synthetic dataset (TinyStories) for comparison. The booklets are typeset using the same codebase that generates the grids used in LLMs Unplugged workshops, but the Library volumes are specifically curated, printed, and hardbound as standalone artefacts.