Build a Reasoning Model (From Scratch)
thg 6 2026 · Được bán bởi Simon and Schuster
star
1 bài đánh giá
Sách điện tử
440
Trang
family_home
Đủ điều kiện
info
Giới thiệu về sách điện tử này
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...
Khám phá thêm
Xếp hạng và đánh giá
1 bài đánh giá
Giới thiệu tác giả
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...
Xếp hạng sách điện tử này
Cho chúng tôi biết suy nghĩ của bạn.
Đọc thông tin
Điện thoại thông minh và máy tính bảng
Cài đặt ứng dụng Google Play Sách cho Android và iPad/iPhone. Ứng dụng sẽ tự động đồng bộ hóa với tài khoản của bạn và cho phép bạn đọc trực tuyến hoặc ngoại tuyến dù cho bạn ở đâu.
Máy tính xách tay và máy tính
Bạn có thể nghe các sách nói đã mua trên Google Play thông qua trình duyệt web trên máy tính.
Thiết bị đọc sách điện tử và các thiết bị khác
Để đọc trên thiết bị e-ink như máy đọc sách điện tử Kobo, bạn sẽ cần tải tệp xuống và chuyển tệp đó sang thiết bị của mình. Hãy làm theo hướng dẫn chi tiết trong Trung tâm trợ giúp để chuyển tệp sang máy đọc sách điện tử được hỗ trợ.
