Là một công cụ AI, rasbt/reasoning-from-scratch đã đạt 5.9k sao trên GitHub, ngôn ngữ Jupyter Notebook. Implement a reasoning LLM in PyTorch from scratch, step by step
Tóm tắt dựng từ metadata GitHub của chính dự án — chưa có bài review TopGit. Trang sẽ tự động cập nhật khi bài review đầy đủ được xuất bản.
VÌ SAO CHƯA CÓ REVIEW
TopGit viết bài đầy đủ cho repo có nhiều sao nhất và được yêu cầu nhiều nhất. Trang này là snapshot trong thời gian chờ — xem README gốc ở tab READ ME.
This repository contains the code for developing an LLM reasoning model and is the official code repository for the book Build a Reasoning Model (From Scratch).
(Printed in color.)
In Build a Reasoning Model (From Scratch), you will learn and understand how a reasoning large language model (LLM) works.
Reasoning is one of the most exciting and important recent advances in improving LLMs, but it’s also one of the easiest to misunderstand if you only hear the term reasoning and read about it in theory. This is why this book takes a hands-on approach. We will start with a pre-trained base LLM and then add reasoning capabilities ourselves, step by step in code, so you can see exactly how it works.
The methods described in this book walk you through the process of developing your own small-but-functional reasoning model for educational purposes. It mirrors the approaches used in creating large-scale reasoning models such as DeepSeek R1, GPT-5 Thinking, and others. In addition, this book includes code for loading the weights of existing, pretrained models.
Link to the official source code repository
Link to the book at Manning (the publisher's website)
Link to the book page on Amazon.com
ISBN 9781633434677
To download a copy of this repository, click on the Download ZIP button or execute the following command in your terminal:
Tip:
Chapter 2 provides additional tips on installing Python, managing Python packages, and setting up your coding environment.
Table of Contents
Troubleshooting Guide
Chapter Title
Main Code
Ch 1: Understanding reasoning Models
No code
Ch 2: Generating Text with a Pre-trained LLM
- ch02_main.ipynb - ch02_exercise-solutions.ipynb
Ch 3: Evaluating Reasoning Models
- ch03_main.ipynb - ch03_exercise-solutions.ipynb
Ch 4: Improving Reasoning with Inference-Time Scaling
- ch04_main.ipynb - ch04_exercise-solutions.ipynb
Ch 5: Inference-Time Scaling via Self-Refinement
- ch05_main.ipynb - ch05_exercise-solutions.ipynb
Ch 6: Training Reasoning Models with Reinforcement Learning
- ch06_main.ipynb - ch06_exercise-solutions.ipynb
Ch 7: Improving GRPO for Reinforcement Learning
- ch07_main.ipynb - ch07_exercise-solutions.ipynb
Ch 8: Distilling Reasoning Models for Efficient Reasoning
- ch08_main.ipynb - ch08_exercise-solutions.ipynb
Appendix A: References and Further Reading
No code
Appendix B: Exercise Solutions
Code and solutions are in each chapter's subfolder
Appendix C: Qwen3 LLM Source Code
- chC_main.ipynb
Appendix D: Using larger LLMs
- chD_main.ipynb
Appendix E: Batching and throughput-oriented execution
- chE_main.ipynb
Appendix F: Common Approaches to LLM Evaluation
- chF_main.ipynb
Appendix G: Building a Chat Interface
- chG
The mental model below summarizes the main techniques covered in this book.
Companion Book
Please note that Build A Reasoning Model (From Scratch) is a standalone book focused on methods to improve LLM reasoning.
In this book, we work with a pre-trained open-source base LLM (Qwen3) on top of which we code apply reasoning methods from scratch. This includes inference-time scaling, reinforcement learning, and distillation.
However, if you are interested in understanding how a conventional base LLM is implemented, you may like my previous book, Build a Large Language Model (From Scratch).
Amazon link
Manning link
GitHub repository
Hardware Requirements
The code in the main chapters of this book is designed to mostly run on consumer hardware within a reasonable timeframe and does not require specialized server hardware. This approach ensures that a wide audience can engage with the material. Additionally, the code automatically utilizes GPUs if they are available. That being said, chapters 2-4 will work well on CPUs and GPUs. For chapters 5 and 6, it is recommended to use a GPU if you want to replicate the results in the chapter.
(Please see the setup_tips doc for additional recommendations.)
Exercises
Each chapter of the book includes several exercises. The solutions are summarized in Appendix B, and the corresponding code notebooks are available in the main chapter folders of this repository (for example, ch02/01_main-chapter-code/ch02_exercise-solutions.ipynb).
Bonus Material
Several folders contain optional materials as a bonus for interested readers:
Chapter 2: Generating Text with a Pre-trained LLM
Optional Python Setup and Cloud GPU Recommendations
Using a GPU-optimized version of the LLM
Using torch.compile() on Windows
Run inference and chat with the model
Chapter 3: Evaluating LLMs
MATH-500 Verifier Scripts
Advanced Parser (hybrid LaTeX parser)
Chapter 4: Improving Reasoning with Inference-Time Scaling
Inference Scaling on MATH-500 (CoT prompting, self-consistency)
Chapter 5: Inference-Time Scaling Via Self-Refinement
More Inference Scaling on MATH-500 (Best-of-N, self-refinement)
Chapter 6: Training Reasoning Models with Reinforcement Learning
GRPO scripts with a batched mode
Chapter 7: Improving GRPO for Reinforcement Learning
Advanced GRPO scripts (including DeepSeek-V3.2-, Olmo3-, and GDPO-style training)
Download training checkpoints (how to download and use the chapter 6 and 7 GRPO checkpoints)
Chapter 8: Distilling Reasoning Models for Efficient Reasoning
Generate distillation data (teacher-output generation via Ollama or OpenRouter)
Train with distillation (including single-example and batched distillation scripts)
Download training checkpoints (how to download and use the chapter 8 distillation checkpoints)
Use Qwen3 with Hugging Face (how to use the base model and chapter 6-8 checkpoints with transformers)
Appendix F: Common Approaches to LLM Evaluation
MMLU Evaluation Methods
LLM leaderboards
LLM-as-a-judge
Appendix G: Building a Chat Interface
Chat interface code
Questions, Feedback, and Contributing to This Repository
For common problems, please see the Troubleshooting Guide.
I welcome all sorts of feedback, best shared via the Manning Discussion Forum or GitHub Discussions. Likewise, if you have any questions or just want to bounce ideas off others, please don't hesitate to post these in the forum as well.
Please note that since this repository contains the code corresponding to a print book, I currently cannot accept contributions that would extend the contents of the main chapter code, as it would introduce deviations from the physical book. Keeping it consistent helps ensure a smooth experience for everyone.
Citation
If you find this book or code useful for your research, please consider citing it.
Chicago-style citation:
Raschka, Sebastian. Build A Reasoning Model (From Scratch). Manning, 2025. ISBN: 9781633434677.
BibTeX entry:
@book{build-llms-from-scratch-book,
author = {Sebastian Raschka},
title = {Build A Reasoning Model (From Scratch)},
publisher = {Manning},
year = {2025},
isbn = {9781633434677},
url = {https://mng.bz/lZ5B},
github = {https://github.com/rasbt/reasoning-from-scratch}
}
Trang TopGit này là một snapshot — tab "Readme" hiển thị nguyên văn README của repo (đã bỏ link, giữ ảnh). Repo GitHub ở github.com/rasbt/reasoning-from-scratch là nguồn chính thức.
rasbt/reasoning-from-scratch có những chủ đề gì?
GitHub topics của rasbt/reasoning-from-scratch: "ai", "artificial-intelligence", "chain-of-thought", "deep-learning", "distillation", "grpo", "inference-time-scaling", "large-language-models", "llm", "llms", "machine-learning", "math-reasoning", "python", "pytorch", "reasoning", "reasoning-models", "reinforcement-learning", "rlhf", "test-time-compute". TopGit xếp repo vào nhóm AI Tools.
rasbt/reasoning-from-scratch có phải mã nguồn mở không?
Có — rasbt/reasoning-from-scratch phát hành theo license Apache-2.0, nghĩa là mã nguồn mở để đọc, fork và (tùy license) tái sử dụng. Mã: github.com/rasbt/reasoning-from-scratch.
rasbt/reasoning-from-scratch có trang demo không?
Dự án có trang chủ ở https://mng.bz/lZ5B. Tab "Readme" ở trang này thường có ảnh chụp và hướng dẫn bắt đầu nhanh.
rasbt/reasoning-from-scratch còn đang phát triển không?
Commit gần nhất trên rasbt/reasoning-from-scratch là 2 tháng trước (theo timestamp GitHub). Repo có 951 fork — một chỉ báo về mức độ quan tâm của cộng đồng.
rasbt/reasoning-from-scratch dùng license gì?
rasbt/reasoning-from-scratch phát hành theo license Apache-2.0. Nên mở file LICENSE trên GitHub để xác nhận — license metadata đôi khi lệch với thực tế dự án.
Đọc đầy đủ README ở tab phía trên.
reasoning-from-scratch có đáng để bạn bỏ thời gian?
ChatGPT, Claude và Perplexity đều đọc được trang này. Hỏi thử xem họ nghĩ gì về reasoning-from-scratch.