SR
Sofia Reyes
2 days ago
Dense but never confusing. Every chapter builds cleanly on the last — you can feel the care in the structure.
Free preview available. Sign in and subscribe to unlock the full book.
Vizuara AI Labs · intermediate
Build Large Language Models (LLMs) from Scratch
Build a GPT-style LLM from an empty file.
From tokenizer to trained transformer: attention, GPT blocks, pretraining, and fine-tuning, built by hand and illustrated.
12 capsules51 figures~3 hoursby Dr. Raj Dandekar
Read on your Kindle or e-reader
Download the EPUB and read offline — perfect for the train. Works on Kindle, Kobo, Apple Books & more.
00LLM Basics6 capsules
LLM Basics — 6 chapters.
01Course Introductionconceptfree12 min02What are LLMs?conceptfree12 min03Pretraining vs Finetuning LLMs🔒12 min04What are transformers?concept🔒14 min05How does GPT-3 really work?🔒13 min06Stages of building an LLM from scratchcode🔒14 min01LLM Attention Mechanism6 capsules
LLM Attention Mechanism — 6 chapters.
07Introduction to the Attention Mechanismconcept🔒11 min08Simplified Attention Mechanism - Code from Scratchcode🔒11 min09The self attention mechanism with keys, query and values: coded form scratchcode🔒12 min10Causal Self Attention - Coded from scratchcode🔒13 min11Multi-head Attention - Part 1🔒13 min12Multi-head Attention - Part 2🔒13 minRatings & reviews
2,225 readersRate this book
HW
Hannah Weiss
3 weeks ago
Practical and rigorous at the same time. I went straight from reading a capsule to shipping it at work.
EP
Elena Petrova
last month
The hand-drawn diagrams make abstract ideas click instantly. Wish every technical book was written like this.