datawhalechina

    datawhalechina/happy-llm

    📚 从零开始构建大模型

    ai-agents
    llm
    agent
    rag
    Jupyter Notebook
    NOASSERTION
    34.8K stars
    3.3K forks
    99 GitHub watchers
    Updated Nov 10, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    No releases in the last 90 days; the most recent was 284 days ago, with 27 contributors on GitHub.

    Use Cases & Benefits

    • Provides a comprehensive tutorial to build and understand large language models from scratch using practical code and theory.
    • Offers a systematic, free, and open-source learning path combining foundational NLP concepts with hands-on LLM implementation and training.
    • Use for university students and researchers seeking to deeply understand LLM architectures and training processes.
    • Use for developers wanting to implement and fine-tune LLaMA2-style models with step-by-step PyTorch guidance.
    • Use for AI practitioners interested in applying advanced LLM techniques like retrieval-augmented generation and intelligent agents.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Other

    GitHub could not identify this license; read the LICENSE file before depending on it.

    Community files

    • README: present

    Watch-outs

    • License not identified by GitHub; read the LICENSE file before depending on it.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    📚 在线阅读地址 📚 从零开始的大语言模型原理与实践教程 深入理解 LLM 核心原理,动手实现你的第一个大模型

      很多小伙伴在看完 Datawhale开源项目: self-llm 开源大模型食用指南 后,感觉意犹未尽,想要深入了解大语言模型的原理和训练过程。于是我们(Datawhale)决定推出《Happy-LLM》项目,旨在帮助大家深入理解大语言模型的原理和训练过程。

      本项目是一个系统性的 LLM 学习教程,将从 NLP 的基本研究方法出发,根据 LLM 的思路及原理逐层深入,依次为读者剖析 LLM 的架构基础和训练过程。同时,我们会结合目前 LLM 领域最主流的代码框架,演练如何亲手搭建、训练一个 LLM,期以实现授之以鱼,更授之以渔。希望大家能从这本书开始走入 LLM 的浩瀚世界,探索 LLM 的无尽可能。

    Excerpt from the datawhalechina/happy-llm README on GitHub (NOASSERTION license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Forks

    3.3K+169

    Open issues

    78+14

    Compared with peers in AI Agents

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    datawhalechina/happy-llm compared with AI Agents repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    morluto/rea450.0K+22.9K7516 days ago
    vercel-labs/agent-desktop21.4K+8.7K755 days ago
    milind-soni/OpenMausBot20.6K+8.4K75today
    stablyai/orca121.4K+6.7K75today
    thedotmack/claude-mem115.8K+4.7K75today
    datawhalechina/happy-llm34.8K—26284 days ago
    Category median115.8K+8.4K75—

    Also by datawhalechina

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description