Build a Reasoning Model (from Scratch) (Paperback)
暫譯: 從零開始建立推理模型 (平裝本)

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

LLM reasoning models have the power to tackle truly challenging problems that require finding the right path through multiple steps. In this book you'll learn how to build a working reasoning model from the ground up. You will start with an existing pre-trained LLM and then implement reasoning-focused improvements from scratch.

Sebastian Raschka, the bestselling author of Build a Large Language Model (From Scratch), is your guide on this exciting journey. Sebastian mentors you every step of the way with clear explanations, practical code, and a keen focus on what really matters. Understand LLM reasoning by creating your own reasoning model-from scratch!

In Build A Reasoning Model (From Scratch) you'll learn how to:

- Implement core reasoning improvements for LLMs
- Evaluate models using judgment-based and benchmark-based methods
- Improve reasoning without updating model weights
- Use reinforcement learning to integrate external tools like calculators
- Apply distillation techniques to learn from larger reasoning models
- Understand the full reasoning model development pipeline

Reasoning models break problems into steps, producing more reliable answers in math, logic, and code. These improvements aren't just a curiosity-they're already integrated into top models like Grok 4 and GPT-5. Build A Reasoning Model (From Scratch) demystifies these complex models with a simple philosophy: the best way to learn how something works is to build it yourself! You'll begin with a pre-trained LLM, adding and improving its reasoning capabilities in ways you can see, test, and understand.

About the book

In Build a Reasoning Model (From Scratch), acclaimed ML research engineer Sebastian Raschka takes you inside the black box of reasoning-enhanced LLMs. You'll start with a compact, pre-trained base model that runs on consumer hardware, then upgrade it step by step to tackle ever-more difficult problems and scenarios. You'll measure its performance, add reasoning at inference time without training, and then improve it further with reinforcement learning. By the end of the book, you'll have a small but capable reasoning stack built from the ground up!

About the reader

For readers who know Python and have some knowledge of machine learning. You won't need any specialist hardware. The examples will run on a standard laptop, although using cloud GPUs can make training faster.

About the author

Sebastian Raschka, PhD, is an LLM Research Engineer with over a decade of experience in artificial intelligence. His work spans industry and academia, including implementing LLM solutions as a senior engineer at Lightning AI and teaching as a statistics professor at the University of Wisconsin-Madison.

Sebastian collaborates with industry partners on AI solutions and serves on the Open Source Board at University of Wisconsin-Madison. He specializes in LLMs and the development of high-performance AI systems, with a deep focus on practical, code-driven implementations. He is the author of the bestselling books Build a Large Language Model (From Scratch), as well as Machine Learning with PyTorch and Scikit-Learn, and Machine Learning Q and AI.