The inner workings of Large Language Models
Free!
Minimum price
$9.99
Suggested price

The inner workings of Large Language Models

how neural networks learn language

About the Book

Large language models like ChatGPT, Claude, and Copilot are changing the way we work, learn, and build software — but how do they actually work?

If you've ever wondered what goes on under the hood of an LLM, this book is for you. It's written by a developer who decided to go deep — and take careful notes along the way.

This book explains how large language models operate, step by step, using clear language and practical illustrations. Whether you're a software developer, tech enthusiast, or simply curious, you'll come away with a strong intuitive understanding of how these models generate text, learn from data, and represent meaning using mathematics.

You'll learn about:

  • Tokenization, embeddings, and vector representations
  • The inner workings of self-attention and transformer layers
  • How models are trained, fine-tuned, and optimized
  • Common myths and misconceptions
  • And much more — including how I used LLMs during my research for the book

This isn't an academic text or a deep dive into every research paper — it's a practical, visual, and approachable explanation for people who want to understand LLMs without getting lost in jargon.

If you're ready to move beyond just using AI and start understanding it, this book will give you a solid foundation

  • Share this book

  • Categories

    • Computers and Programming
    • Neural Networks
    • Machine Learning
    • Deep Learning
    • Computer Science
    • Artificial Intelligence
    • Sciences
  • Feedback

    Email the Author(s)

About the Author

Roger Gullhaug
Roger Gullhaug

Roger Gullhaug is Director of Development and Operations at RamBase (Jakob Hatteland Computer AS). He is responsible for a team of 60 developers, architects, testers and devops engineers.

A technologist at heart, he combines two decades of software-development experience with a passion for nurturing people and building high-performing teams.

Table of Contents

  • About this book
  • About the author
  • Part I – Foundations of Language Models
    • It is all about predicting the next word, one word at a time
    • Tokenization: How text becomes numbers
    • Embeddings: From tokens to vectors
    • Byte pair encoding: Handling unknown words
    • Training an LLM: What data is needed for training?
    • Embedding lookup
    • Position matrix
    • Attention mechanisms
    • Self-attention with trainable weights
    • Causal attention
    • Multi-Head Attention
    • Layer normalization (layer norm)
    • FeedForward (aka MLP)
    • Transformer blocks and layers
    • The full transformer block
    • What is a logit, and how is it calculated?
    • Picking the next token
  • Part II – Making the model useful
    • Time for pre-training
    • Calculating loss and adjusting parameters
    • Backpropagation
    • Fine tuning
    • Quick Reference table: How LLMs work in 8 steps
    • What about reasoning models?
    • Can I teach an LLM new things it doesn’t already know?
    • Do we now understand how AI actually works
  • Part III – Reflection and practical use
    • Do LLMs really understand language?
    • Why do LLMs make mistakes?
    • Why LLMs will soon be so much more than a chatbot
    • How I have been using LLMs during my research
    • Final thoughts
    • Resources for further learning
    • Glossary

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.

You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!

So, there's no reason not to click the Add to Cart button, is there?

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

In fact, authors have earnedover $14 millionwriting, publishing and selling on Leanpub.

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub