Book series
Building Large Language Models
Building Large Language Models is a comprehensive four-volume series designed for software engineers, AI practitioners, and technical professionals who want to understand how mode...
4 books
Building Large Language Models
Building Large Language Models is a comprehensive four-volume series designed for software engineers, AI practitioners, and technical professionals who want to understand how modern language models are built from the ground up.
The series follows the complete lifecycle of a Large Language Model, from the fundamental concepts of language representation and neural networks, through dataset construction and large-scale training, to inference, deployment, and production AI systems.
Rather than focusing on how to use AI tools, this series focuses on how AI systems are created. Readers will learn the principles, engineering decisions, and system architectures behind modern models such as GPT, Llama, Qwen, and DeepSeek.
By completing the series, readers will gain a practical understanding of the technologies that power today's AI revolution and develop the knowledge needed to transition from software engineering to AI engineering.
The series consists of four volumes:
Volume I — The Foundations of Large Language Models
Volume II — The Data Behind Large Language Models
Volume III — Training Large Language Models
Volume IV — Large Language Model Systems
Books in this series
Book 1
Data for Large Language Models Collecting, Cleaning, and Scaling the Fuel of AI
Miles Thornton
Book 1
Data for Large Language Models Collecting, Cleaning, and Scaling the Fuel of AI
Miles Thornton
Every major advance in large language models over the past five years—from GPT-4 to LLaMA 3—was driven not by a cleverer architecture, but by a better dataset. The Chinchilla scaling law proved that most models are trained on far too few tokens relative to th...
Book 2
Systems for Large Language Models: Inference, Agents, and Production AI Infrastructure
Miles Thornton
Book 2
Systems for Large Language Models: Inference, Agents, and Production AI Infrastructure
Miles Thornton
Your GPT-4 deployment is using less than 30% of your GPU capacity. Your latency spikes are unpredictable, and your team spends more time debugging infrastructure than shipping features. This is the reality of production AI that no one talks about until after...
Book 3
The Foundations of Large Language Models Understanding Language, Neural Networks, and Transformers
Miles Thornton
Book 3
The Foundations of Large Language Models Understanding Language, Neural Networks, and Transformers
Miles Thornton
Large language models generate fluent text, but they don't understand a single word. How can a machine that merely predicts the next token produce coherent paragraphs, answer questions, and even write code? The answer lies in a carefully engineered stack of r...
Book 4
Training Large Language Models Pretraining, Alignment, and Scaling Modern AI
Miles Thornton
Book 4
Training Large Language Models Pretraining, Alignment, and Scaling Modern AI
Miles Thornton
Most large language model training runs don't crash because of bad math—they crash because of bad engineering. The difference between a successful 1000-GPU run and a costly failure often comes down to understanding how compute, memory, and bandwidth interact...