Build a Reasoning Model (From Scratch)
2026年6月 · 销售商：Simon and Schuster
star
1 条评价
电子书
440
页
family_home
符合条件
info
关于此电子书
Get the eBook free when you register your print book at Manning.
"An exceptional deep dive into the next frontier of AI.”
—Aman Chadha, Google
This book is a practical guide to understanding how modern reasoning-oriented LLMs work by building their core methods step by step. The book tells a clear engineering story: start with a conventional pre-trained LLM, learn how text generation works, build reliable evaluation tools, improve reasoning through inference-time methods, then move into training-based approaches such as reinforcement learning and distillation.
The progression is deliberate. Early chapters establish the baseline model and explain text generation, KV caching, and evaluation with math verifiers. The middle chapters show how reasoning can be improved without changing model weights, using chain-of-thought prompting, sampling, self-consistency, response scoring, and self-refinement. Later chapters move to changing the model itself through reinforcement learning with verifiable rewards, GRPO improvements, format rewards, and finally distillation from stronger reasoning models into smaller ones.
The book is especially useful because it implements the core methods from scratch rather than treating them as black-box library calls. Readers see how self-consistency, self-refinement, Best-of-N, and training-based methods actually work, including their cost and latency trade-offs. It also discusses common failure modes, including cases where refinement can make answers worse. Difficult concepts such as softmax, temperature, and top-p sampling are clarified with code-linked explanations and diagrams, and visual workflows make pipelines and scoring methods easier to follow.
Reading the book feels like following a guided technical build rather than a loose survey of AI topics. Each concept is introduced because the project now needs it. Diagrams, roadmaps, code listings, exercises, and repeated workflow summaries help readers stay oriented through advanced material. This structure reflects Sebastian Raschka’s professional strength: explaining complex machine learning topics by making every detail concrete and showing exactly where each section fits in the larger story. He does not treat mechanisms like evaluation, log-probabilities, KL regularization, or distillation as isolated abstractions; he connects them to the goal of making reasoning models understandable and implementable.
Physically and organizationally, the book has eight chapters and seven substantial appendixes. That design keeps the main narrative focused while moving supporting material like references, exercise solutions, model source code, larger models, batching, evaluation alternatives, and chat interfaces into ordered appendixes. The result is a logically flowing book that remains hands-on, navigable, and technically deep without constantly interrupting the central build.
What's inside
• From-scratch implementations of core LLM reasoning improvements
• Verifier-based evaluation methods
• RL with automatic verifiers for mathematics tasks
About the reader
For readers who know Python and have some knowledge of machine learning.
About the author
Sebastian Raschka is an LLM Research Engineer with over a decade of experience. He is the author of the bestselling book Build a Large Language Model (From Scratch).
"An exceptional deep dive into the next frontier of AI.”
—Aman Chadha, Google
This book is a practical guide to understanding how modern reasoning-oriented LLMs work by building their core methods step by step. The book tells a clear engineering story: start with a conventional pre-trained LLM, learn how text generation works, build reliable evaluation tools, improve reasoning through inference-time methods, then move into training-based approaches such as reinforcement learning and distillation.
The progression is deliberate. Early chapters establish the baseline model and explain text generation, KV caching, and evaluation with math verifiers. The middle chapters show how reasoning can be improved without changing model weights, using chain-of-thought prompting, sampling, self-consistency, response scoring, and self-refinement. Later chapters move to changing the model itself through reinforcement learning with verifiable rewards, GRPO improvements, format rewards, and finally distillation from stronger reasoning models into smaller ones.
The book is especially useful because it implements the core methods from scratch rather than treating them as black-box library calls. Readers see how self-consistency, self-refinement, Best-of-N, and training-based methods actually work, including their cost and latency trade-offs. It also discusses common failure modes, including cases where refinement can make answers worse. Difficult concepts such as softmax, temperature, and top-p sampling are clarified with code-linked explanations and diagrams, and visual workflows make pipelines and scoring methods easier to follow.
Reading the book feels like following a guided technical build rather than a loose survey of AI topics. Each concept is introduced because the project now needs it. Diagrams, roadmaps, code listings, exercises, and repeated workflow summaries help readers stay oriented through advanced material. This structure reflects Sebastian Raschka’s professional strength: explaining complex machine learning topics by making every detail concrete and showing exactly where each section fits in the larger story. He does not treat mechanisms like evaluation, log-probabilities, KL regularization, or distillation as isolated abstractions; he connects them to the goal of making reasoning models understandable and implementable.
Physically and organizationally, the book has eight chapters and seven substantial appendixes. That design keeps the main narrative focused while moving supporting material like references, exercise solutions, model source code, larger models, batching, evaluation alternatives, and chat interfaces into ordered appendixes. The result is a logically flowing book that remains hands-on, navigable, and technically deep without constantly interrupting the central build.
What's inside
• From-scratch implementations of core LLM reasoning improvements
• Verifier-based evaluation methods
• RL with automatic verifiers for mathematics tasks
About the reader
For readers who know Python and have some knowledge of machine learning.
About the author
Sebastian Raschka is an LLM Research Engineer with over a decade of experience. He is the author of the bestselling book Build a Large Language Model (From Scratch).
Get the eBook free when you register your print book at Manning.
"An exceptional deep dive into the next frontier of AI.”
—Aman Chadha, Google
This book is a practical guide to understanding how modern reasoning-oriented LLMs work by building their core methods step by step. The book tells a cl...
探索更多
评分和评价
1 条评价
作者简介
Sebastian Raschka has been working on machine learning and AI for more than a decade. Sebastian joined Lightning AI in 2022, where he now focuses on AI and LLM research, developing open-source software, and creating educational material. Prior to that, Sebastian worked at the University of Wisconsin-Madison as an assistant professor in the Department of Statistics, focusing on deep learning and machine learning research. He has a strong passion for education and is best known for his bestselling books on machine learning using open-source software.
Sebastian Raschka has been working on machine learning and AI for more than a decade. Sebastian joined Lightning AI in 2022, where he now focuses on AI and LLM research, developing open-source software, and creating educational material. Prior to that, Sebastian worked at the University of Wiscon...
为此电子书评分
欢迎向我们提供反馈意见。
如何阅读
智能手机和平板电脑
笔记本电脑和台式机
您可以使用计算机的网络浏览器聆听您在 Google Play 购买的有声读物。
电子阅读器和其他设备
如果要在 Kobo 电子阅读器等电子墨水屏设备上阅读，您需要下载一个文件，并将其传输到相应设备上。若要将文件传输到受支持的电子阅读器上，请按帮助中心内的详细说明操作。
