Repolode
Submit
NiuTrans

NiuTrans/NLPBook

A free open book covering neural networks and large language models for NLP, from machine learning basics through prompting, alignment and reasoning.

View on GitHub
Stars
891
Forks
153
Open issues
10
Last commit
2 days ago

What is it?

This is a textbook on natural language processing with neural networks and large language models, written by Tong Xiao and Jingbo Zhu. It is organized in three parts: preliminaries on machine learning and neural networks, basic sequence models including word vectors, recurrent and convolutional models, sequence-to-sequence models and Transformers, and large language models covering pre-training, generative models, prompting, alignment, inference and reasoning.

Each chapter is published as a separate PDF, and a complete PDF of the whole book is also available. Some chapters are adapted from the authors' earlier papers on Transformers and foundations of large language models, with substantial new material added. The book is also available as an online site.

The content is aimed at anyone interested in NLP and deep learning. Translations into Chinese, Japanese, French, German, Italian and Portuguese are maintained in a separate repository.

Key features

  • 01Covers machine learning and neural network foundations before moving to language models
  • 02Explains Transformers, sequence-to-sequence models and word vectors
  • 03Includes later chapters on pre-training, prompting, alignment, inference and reasoning
  • 04Available as per-chapter PDFs, a full PDF and an online site
  • 05Provides a BibTeX citation entry

Use cases

  • Learning NLP and deep learning from fundamentals to modern large language models
  • Reviewing the theory behind Transformers and LLM training stages
  • Using as a reference or course material with citable chapters
  • Reading the book in a language other than English through the translation repository

Quick start

  1. 1

    Open the online version of the book in your browser

  2. 2

    Download the complete PDF of the book from the chapters folder

Things to know

  • No license is stated in the project metadata.

Topics

#deep-learning#natural-language-processing#large-language-models#neural-networks#transformers#textbook

FAQ

What is NLPBook?
A free open book covering neural networks and large language models for NLP, from machine learning basics through prompting, alignment and reasoning. This is a textbook on natural language processing with neural networks and large language models, written by Tong Xiao and Jingbo Zhu. It is organized in three parts: preliminaries on machine learning and neural networks, basic sequence models including word vectors, recurrent and convolutional models, sequence-to-sequence models and Transformers, and large language models covering pre-training, generative models, prompting, alignment, inference and reasoning.
Is NLPBook free to use? What license does it have?
NLPBook has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
Is NLPBook still maintained?
Actively maintained. The last commit to NLPBook was on Oct 19, 2026.
What can I use NLPBook for?
Learning NLP and deep learning from fundamentals to modern large language models Reviewing the theory behind Transformers and LLM training stages Using as a reference or course material with citable chapters Reading the book in a language other than English through the translation repository
How do I install NLPBook?
Open the online version of the book in your browser Download the complete PDF of the book from the chapters folder
Where can I get NLPBook?
The source code and installation instructions are on GitHub: https://github.com/NiuTrans/NLPBook

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects