Textbook in PDF format
Understand how LLMs reason by creating your own reasoning model from scratch. In the book "Building a Reasoning Model from Scratch", you will step-by-step build a working reasoning model on top of a compact pre-trained LLM. Your mentor, Sebastian Raschka, author of the bestseller Build a Large Language Model (From Scratch), guides you through the entire process: from basic architecture to practical improvements, with clear explanations and applied code.
You will learn to:
– implement key improvements for reasoning in LLM;
– evaluate models using expert judgments and benchmarks;
– enhance the ability to reason without retraining weights;
– connect external tools (e.g., calculator) through RL;
– apply knowledge distillation from larger reasoning models;
– understand and build a complete development pipeline for reasoning models.
Reasoning models break down tasks into steps and provide more reliable answers in mathematics, logic, and programming - an approach already used in leading systems like Grok 4 and GPT-5. This course demystifies the process: you will start with a small foundational LLM, incrementally add reasoning mechanisms, learn to measure real quality improvements, and then further enhance it using non-training methods and RL. By the end, you will have a compact but capable reasoning stack, created by your own hands