
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Stars: 72995

This repository contains the code for coding, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book Build a Large Language Model (From Scratch). In _Build a Large Language Model (From Scratch)_, you'll discover how LLMs work from the inside out. In this book, I'll guide you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples. The method described in this book for training and developing your own small-but-functional model for educational purposes mirrors the approach used in creating large-scale foundational models such as those behind ChatGPT.
README:
This repository contains the code for developing, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book Build a Large Language Model (From Scratch).
In Build a Large Language Model (From Scratch), you'll learn and understand how large language models (LLMs) work from the inside out by coding them from the ground up, step by step. In this book, I'll guide you through creating your own LLM, explaining each stage with clear text, diagrams, and examples.
The method described in this book for training and developing your own small-but-functional model for educational purposes mirrors the approach used in creating large-scale foundational models such as those behind ChatGPT. In addition, this book includes code for loading the weights of larger pretrained models for finetuning.
- 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 9781633437166
To download a copy of this repository, click on the Download ZIP button or execute the following command in your terminal:
git clone --depth 1 https://github.com/rasbt/LLMs-from-scratch.git
(If you downloaded the code bundle from the Manning website, please consider visiting the official code repository on GitHub at https://github.com/rasbt/LLMs-from-scratch for the latest updates.)
Please note that this README.md
file is a Markdown (.md
) file. If you have downloaded this code bundle from the Manning website and are viewing it on your local computer, I recommend using a Markdown editor or previewer for proper viewing. If you haven't installed a Markdown editor yet, Ghostwriter is a good free option.
You can alternatively view this and other files on GitHub at https://github.com/rasbt/LLMs-from-scratch in your browser, which renders Markdown automatically.
Tip: If you're seeking guidance on installing Python and Python packages and setting up your code environment, I suggest reading the README.md file located in the setup directory.
Chapter Title | Main Code (for Quick Access) | All Code + Supplementary |
---|---|---|
Setup recommendations | - | - |
Ch 1: Understanding Large Language Models | No code | - |
Ch 2: Working with Text Data | - ch02.ipynb - dataloader.ipynb (summary) - exercise-solutions.ipynb |
./ch02 |
Ch 3: Coding Attention Mechanisms | - ch03.ipynb - multihead-attention.ipynb (summary) - exercise-solutions.ipynb |
./ch03 |
Ch 4: Implementing a GPT Model from Scratch | - ch04.ipynb - gpt.py (summary) - exercise-solutions.ipynb |
./ch04 |
Ch 5: Pretraining on Unlabeled Data | - ch05.ipynb - gpt_train.py (summary) - gpt_generate.py (summary) - exercise-solutions.ipynb |
./ch05 |
Ch 6: Finetuning for Text Classification | - ch06.ipynb - gpt_class_finetune.py - exercise-solutions.ipynb |
./ch06 |
Ch 7: Finetuning to Follow Instructions | - ch07.ipynb - gpt_instruction_finetuning.py (summary) - ollama_evaluate.py (summary) - exercise-solutions.ipynb |
./ch07 |
Appendix A: Introduction to PyTorch | - code-part1.ipynb - code-part2.ipynb - DDP-script.py - exercise-solutions.ipynb |
./appendix-A |
Appendix B: References and Further Reading | No code | - |
Appendix C: Exercise Solutions | No code | - |
Appendix D: Adding Bells and Whistles to the Training Loop | - appendix-D.ipynb | ./appendix-D |
Appendix E: Parameter-efficient Finetuning with LoRA | - appendix-E.ipynb | ./appendix-E |
The mental model below summarizes the contents covered in this book.
The most important prerequisite is a strong foundation in Python programming. With this knowledge, you will be well prepared to explore the fascinating world of LLMs and understand the concepts and code examples presented in this book.
If you have some experience with deep neural networks, you may find certain concepts more familiar, as LLMs are built upon these architectures.
This book uses PyTorch to implement the code from scratch without using any external LLM libraries. While proficiency in PyTorch is not a prerequisite, familiarity with PyTorch basics is certainly useful. If you are new to PyTorch, Appendix A provides a concise introduction to PyTorch. Alternatively, you may find my book, PyTorch in One Hour: From Tensors to Training Neural Networks on Multiple GPUs, helpful for learning about the essentials.
The code in the main chapters of this book is designed to run on conventional laptops within a reasonable timeframe and does not require specialized hardware. This approach ensures that a wide audience can engage with the material. Additionally, the code automatically utilizes GPUs if they are available. (Please see the setup doc for additional recommendations.)
A 17-hour and 15-minute companion video course where I code through each chapter of the book. The course is organized into chapters and sections that mirror the book's structure so that it can be used as a standalone alternative to the book or complementary code-along resource.
Build A Reasoning Model (From Scratch), while a standalone book, can be considered as a sequel to Build A Large Language Model (From Scratch).
It starts with a pretrained model and implements different reasoning approaches, including inference-time scaling, reinforcement learning, and distillation, to improve the model's reasoning capabilities.
Similar to Build A Large Language Model (From Scratch), Build A Reasoning Model (From Scratch) takes a hands-on approach implementing these methods from scratch.
- Amazon link (TBD)
- Manning link
- GitHub repository
Each chapter of the book includes several exercises. The solutions are summarized in Appendix C, and the corresponding code notebooks are available in the main chapter folders of this repository (for example, ./ch02/01_main-chapter-code/exercise-solutions.ipynb.
In addition to the code exercises, you can download a free 170-page PDF titled Test Yourself On Build a Large Language Model (From Scratch) from the Manning website. It contains approximately 30 quiz questions and solutions per chapter to help you test your understanding.
Several folders contain optional materials as a bonus for interested readers:
- Setup
- Chapter 2: Working with text data
- Chapter 3: Coding attention mechanisms
- Chapter 4: Implementing a GPT model from scratch
-
Chapter 5: Pretraining on unlabeled data:
- Alternative Weight Loading Methods
- Pretraining GPT on the Project Gutenberg Dataset
- Adding Bells and Whistles to the Training Loop
- Optimizing Hyperparameters for Pretraining
- Building a User Interface to Interact With the Pretrained LLM
- Converting GPT to Llama
- Llama 3.2 From Scratch
- Qwen3 Dense and Mixture-of-Experts (MoE) From Scratch
- Gemma 3 From Scratch
- Memory-efficient Model Weight Loading
- Extending the Tiktoken BPE Tokenizer with New Tokens
- PyTorch Performance Tips for Faster LLM Training
- Chapter 6: Finetuning for classification
-
Chapter 7: Finetuning to follow instructions
- Dataset Utilities for Finding Near Duplicates and Creating Passive Voice Entries
- Evaluating Instruction Responses Using the OpenAI API and Ollama
- Generating a Dataset for Instruction Finetuning
- Improving a Dataset for Instruction Finetuning
- Generating a Preference Dataset with Llama 3.1 70B and Ollama
- Direct Preference Optimization (DPO) for LLM Alignment
- Building a User Interface to Interact With the Instruction Finetuned GPT Model
I welcome all sorts of feedback, best shared via the Manning 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.
If you find this book or code useful for your research, please consider citing it.
Chicago-style citation:
Raschka, Sebastian. Build A Large Language Model (From Scratch). Manning, 2024. ISBN: 978-1633437166.
BibTeX entry:
@book{build-llms-from-scratch-book,
author = {Sebastian Raschka},
title = {Build A Large Language Model (From Scratch)},
publisher = {Manning},
year = {2024},
isbn = {978-1633437166},
url = {https://www.manning.com/books/build-a-large-language-model-from-scratch},
github = {https://github.com/rasbt/LLMs-from-scratch}
}
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for LLMs-from-scratch
Similar Open Source Tools

LLMs-from-scratch
This repository contains the code for coding, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book Build a Large Language Model (From Scratch). In _Build a Large Language Model (From Scratch)_, you'll discover how LLMs work from the inside out. In this book, I'll guide you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples. The method described in this book for training and developing your own small-but-functional model for educational purposes mirrors the approach used in creating large-scale foundational models such as those behind ChatGPT.

reasoning-from-scratch
This repository contains the code for developing a large language model (LLM) reasoning model. The book 'Build a Reasoning Model (From Scratch)' provides a hands-on approach to understanding and implementing reasoning capabilities in LLMs. It guides users through creating a small but functional reasoning model, mirroring approaches used in large-scale models like DeepSeek R1 and GPT-5 Thinking. The code includes methods for loading weights of pretrained models.

venice
Venice is a derived data storage platform, providing the following characteristics: 1. High throughput asynchronous ingestion from batch and streaming sources (e.g. Hadoop and Samza). 2. Low latency online reads via remote queries or in-process caching. 3. Active-active replication between regions with CRDT-based conflict resolution. 4. Multi-cluster support within each region with operator-driven cluster assignment. 5. Multi-tenancy, horizontal scalability and elasticity within each cluster. The above makes Venice particularly suitable as the stateful component backing a Feature Store, such as Feathr. AI applications feed the output of their ML training jobs into Venice and then query the data for use during online inference workloads.

Reflection_Tuning
Reflection-Tuning is a project focused on improving the quality of instruction-tuning data through a reflection-based method. It introduces Selective Reflection-Tuning, where the student model can decide whether to accept the improvements made by the teacher model. The project aims to generate high-quality instruction-response pairs by defining specific criteria for the oracle model to follow and respond to. It also evaluates the efficacy and relevance of instruction-response pairs using the r-IFD metric. The project provides code for reflection and selection processes, along with data and model weights for both V1 and V2 methods.

llm-course
The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

repromodel
ReproModel is an open-source toolbox designed to boost AI research efficiency by enabling researchers to reproduce, compare, train, and test AI models faster. It provides standardized models, dataloaders, and processing procedures, allowing researchers to focus on new datasets and model development. With a no-code solution, users can access benchmark and SOTA models and datasets, utilize training visualizations, extract code for publication, and leverage an LLM-powered automated methodology description writer. The toolbox helps researchers modularize development, compare pipeline performance reproducibly, and reduce time for model development, computation, and writing. Future versions aim to facilitate building upon state-of-the-art research by loading previously published study IDs with verified code, experiments, and results stored in the system.

ludwig
Ludwig is a declarative deep learning framework designed for scale and efficiency. It is a low-code framework that allows users to build custom AI models like LLMs and other deep neural networks with ease. Ludwig offers features such as optimized scale and efficiency, expert level control, modularity, and extensibility. It is engineered for production with prebuilt Docker containers, support for running with Ray on Kubernetes, and the ability to export models to Torchscript and Triton. Ludwig is hosted by the Linux Foundation AI & Data.

nous
Nous is an open-source TypeScript platform for autonomous AI agents and LLM based workflows. It aims to automate processes, support requests, review code, assist with refactorings, and more. The platform supports various integrations, multiple LLMs/services, CLI and web interface, human-in-the-loop interactions, flexible deployment options, observability with OpenTelemetry tracing, and specific agents for code editing, software engineering, and code review. It offers advanced features like reasoning/planning, memory and function call history, hierarchical task decomposition, and control-loop function calling options. Nous is designed to be a flexible platform for the TypeScript community to expand and support different use cases and integrations.

NeMo
NVIDIA NeMo Framework is a scalable and cloud-native generative AI framework built for researchers and PyTorch developers working on Large Language Models (LLMs), Multimodal Models (MMs), Automatic Speech Recognition (ASR), Text to Speech (TTS), and Computer Vision (CV) domains. It is designed to help you efficiently create, customize, and deploy new generative AI models by leveraging existing code and pre-trained model checkpoints.

CogVideo
CogVideo is an open-source repository that provides pretrained text-to-video models for generating videos based on input text. It includes models like CogVideoX-2B and CogVideo, offering powerful video generation capabilities. The repository offers tools for inference, fine-tuning, and model conversion, along with demos showcasing the model's capabilities through CLI, web UI, and online experiences. CogVideo aims to facilitate the creation of high-quality videos from textual descriptions, catering to a wide range of applications.

oat
Oat is a simple and efficient framework for running online LLM alignment algorithms. It implements a distributed Actor-Learner-Oracle architecture, with components optimized using state-of-the-art tools. Oat simplifies the experimental pipeline of LLM alignment by serving an Oracle online for preference data labeling and model evaluation. It provides a variety of oracles for simulating feedback and supports verifiable rewards. Oat's modular structure allows for easy inheritance and modification of classes, enabling rapid prototyping and experimentation with new algorithms. The framework implements cutting-edge online algorithms like PPO for math reasoning and various online exploration algorithms.

NeMo-Curator
NeMo Curator is a GPU-accelerated open-source framework designed for efficient large language model data curation. It provides scalable dataset preparation for tasks like foundation model pretraining, domain-adaptive pretraining, supervised fine-tuning, and parameter-efficient fine-tuning. The library leverages GPUs with Dask and RAPIDS to accelerate data curation, offering customizable and modular interfaces for pipeline expansion and model convergence. Key features include data download, text extraction, quality filtering, deduplication, downstream-task decontamination, distributed data classification, and PII redaction. NeMo Curator is suitable for curating high-quality datasets for large language model training.

model2vec
Model2Vec is a technique to turn any sentence transformer into a really small static model, reducing model size by 15x and making the models up to 500x faster, with a small drop in performance. It outperforms other static embedding models like GLoVe and BPEmb, is lightweight with only `numpy` as a major dependency, offers fast inference, dataset-free distillation, and is integrated into Sentence Transformers, txtai, and Chonkie. Model2Vec creates powerful models by passing a vocabulary through a sentence transformer model, reducing dimensionality using PCA, and weighting embeddings using zipf weighting. Users can distill their own models or use pre-trained models from the HuggingFace hub. Evaluation can be done using the provided evaluation package. Model2Vec is licensed under MIT.

fluid
Fluid is an open source Kubernetes-native Distributed Dataset Orchestrator and Accelerator for data-intensive applications, such as big data and AI applications. It implements dataset abstraction, scalable cache runtime, automated data operations, elasticity and scheduling, and is runtime platform agnostic. Key concepts include Dataset and Runtime. Prerequisites include Kubernetes version > 1.16, Golang 1.18+, and Helm 3. The tool offers features like accelerating remote file accessing, machine learning, accelerating PVC, preloading dataset, and on-the-fly dataset cache scaling. Contributions are welcomed, and the project is under the Apache 2.0 license with a vendor-neutral approach.

HAMi
HAMi is a Heterogeneous AI Computing Virtualization Middleware designed to manage Heterogeneous AI Computing Devices in a Kubernetes cluster. It allows for device sharing, device memory control, device type specification, and device UUID specification. The tool is easy to use and does not require modifying task YAML files. It includes features like hard limits on device memory, partial device allocation, streaming multiprocessor limits, and core usage specification. HAMi consists of components like a mutating webhook, scheduler extender, device plugins, and in-container virtualization techniques. It is suitable for scenarios requiring device sharing, specific device memory allocation, GPU balancing, low utilization optimization, and scenarios needing multiple small GPUs. The tool requires prerequisites like NVIDIA drivers, CUDA version, nvidia-docker, Kubernetes version, glibc version, and helm. Users can install, upgrade, and uninstall HAMi, submit tasks, and monitor cluster information. The tool's roadmap includes supporting additional AI computing devices, video codec processing, and Multi-Instance GPUs (MIG).

babilong
BABILong is a generative benchmark designed to evaluate the performance of NLP models in processing long documents with distributed facts. It consists of 20 tasks that simulate interactions between characters and objects in various locations, requiring models to distinguish important information from irrelevant details. The tasks vary in complexity and reasoning aspects, with test samples potentially containing millions of tokens. The benchmark aims to challenge and assess the capabilities of Large Language Models (LLMs) in handling complex, long-context information.
For similar tasks

awesome-transformer-nlp
This repository contains a hand-curated list of great machine (deep) learning resources for Natural Language Processing (NLP) with a focus on Generative Pre-trained Transformer (GPT), Bidirectional Encoder Representations from Transformers (BERT), attention mechanism, Transformer architectures/networks, Chatbot, and transfer learning in NLP.

LLMs-from-scratch
This repository contains the code for coding, pretraining, and finetuning a GPT-like LLM and is the official code repository for the book Build a Large Language Model (From Scratch). In _Build a Large Language Model (From Scratch)_, you'll discover how LLMs work from the inside out. In this book, I'll guide you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples. The method described in this book for training and developing your own small-but-functional model for educational purposes mirrors the approach used in creating large-scale foundational models such as those behind ChatGPT.

PaddleNLP
PaddleNLP is an easy-to-use and high-performance NLP library. It aggregates high-quality pre-trained models in the industry and provides out-of-the-box development experience, covering a model library for multiple NLP scenarios with industry practice examples to meet developers' flexible customization needs.

Tutorial
The Bookworm·Puyu large model training camp aims to promote the implementation of large models in more industries and provide developers with a more efficient platform for learning the development and application of large models. Within two weeks, you will learn the entire process of fine-tuning, deploying, and evaluating large models.

llms-from-scratch-cn
This repository provides a detailed tutorial on how to build your own large language model (LLM) from scratch. It includes all the code necessary to create a GPT-like LLM, covering the encoding, pre-training, and fine-tuning processes. The tutorial is written in a clear and concise style, with plenty of examples and illustrations to help you understand the concepts involved. It is suitable for developers and researchers with some programming experience who are interested in learning more about LLMs and how to build them.

LLMBook-zh.github.io
This book aims to provide readers with a comprehensive understanding of large language model technology, including its basic principles, key technologies, and application prospects. Through in-depth research and practice, we can continuously explore and improve large language model technology, and contribute to the development of the field of artificial intelligence.

LLM-Blender
LLM-Blender is a framework for ensembling large language models (LLMs) to achieve superior performance. It consists of two modules: PairRanker and GenFuser. PairRanker uses pairwise comparisons to distinguish between candidate outputs, while GenFuser merges the top-ranked candidates to create an improved output. LLM-Blender has been shown to significantly surpass the best LLMs and baseline ensembling methods across various metrics on the MixInstruct benchmark dataset.

SeaLLMs
SeaLLMs are a family of language models optimized for Southeast Asian (SEA) languages. They were pre-trained from Llama-2, on a tailored publicly-available dataset, which comprises texts in Vietnamese 🇻🇳, Indonesian 🇮🇩, Thai 🇹🇭, Malay 🇲🇾, Khmer🇰🇭, Lao🇱🇦, Tagalog🇵🇭 and Burmese🇲🇲. The SeaLLM-chat underwent supervised finetuning (SFT) and specialized self-preferencing DPO using a mix of public instruction data and a small number of queries used by SEA language native speakers in natural settings, which **adapt to the local cultural norms, customs, styles and laws in these areas**. SeaLLM-13b models exhibit superior performance across a wide spectrum of linguistic tasks and assistant-style instruction-following capabilities relative to comparable open-source models. Moreover, they outperform **ChatGPT-3.5** in non-Latin languages, such as Thai, Khmer, Lao, and Burmese.
For similar jobs

LLM-FineTuning-Large-Language-Models
This repository contains projects and notes on common practical techniques for fine-tuning Large Language Models (LLMs). It includes fine-tuning LLM notebooks, Colab links, LLM techniques and utils, and other smaller language models. The repository also provides links to YouTube videos explaining the concepts and techniques discussed in the notebooks.

lloco
LLoCO is a technique that learns documents offline through context compression and in-domain parameter-efficient finetuning using LoRA, which enables LLMs to handle long context efficiently.

camel
CAMEL is an open-source library designed for the study of autonomous and communicative agents. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

llm-baselines
LLM-baselines is a modular codebase to experiment with transformers, inspired from NanoGPT. It provides a quick and easy way to train and evaluate transformer models on a variety of datasets. The codebase is well-documented and easy to use, making it a great resource for researchers and practitioners alike.

python-tutorial-notebooks
This repository contains Jupyter-based tutorials for NLP, ML, AI in Python for classes in Computational Linguistics, Natural Language Processing (NLP), Machine Learning (ML), and Artificial Intelligence (AI) at Indiana University.

EvalAI
EvalAI is an open-source platform for evaluating and comparing machine learning (ML) and artificial intelligence (AI) algorithms at scale. It provides a central leaderboard and submission interface, making it easier for researchers to reproduce results mentioned in papers and perform reliable & accurate quantitative analysis. EvalAI also offers features such as custom evaluation protocols and phases, remote evaluation, evaluation inside environments, CLI support, portability, and faster evaluation.

Weekly-Top-LLM-Papers
This repository provides a curated list of weekly published Large Language Model (LLM) papers. It includes top important LLM papers for each week, organized by month and year. The papers are categorized into different time periods, making it easy to find the most recent and relevant research in the field of LLM.

self-llm
This project is a Chinese tutorial for domestic beginners based on the AutoDL platform, providing full-process guidance for various open-source large models, including environment configuration, local deployment, and efficient fine-tuning. It simplifies the deployment, use, and application process of open-source large models, enabling more ordinary students and researchers to better use open-source large models and helping open and free large models integrate into the lives of ordinary learners faster.