#1414th of 14 in Learning and cookbooks
hands-on-large-language-models
Companion notebooks for the O'Reilly book Hands-On Large Language Models
- Stars
- 29.6k
- License
- Apache-2.0
- Last commit
- Apr 2026
- Language
- Jupyter Notebook
24,095 on 24 Mar 202629,588 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Code for every example in the book by Jay Alammar and Maarten Grootendorst, as one Jupyter notebook per chapter. Chapters cover tokens and embeddings, transformer internals, classification, clustering, prompt engineering, semantic search and RAG, multimodal models, and fine-tuning. Notebooks were built and tested on Google Colab with a free 16GB T4 GPU.
Who it is for: Developers learning how LLMs work who want runnable chapter code
Strengths
- One notebook per chapter (12), each with an Open in Colab link
- Covers embeddings, RAG, multimodal models and fine-tuning of BERT and generation models
- Tested mainly on free Colab T4 16GB, so no local GPU is required
- Bonus folder links to visual guides on Mamba, quantization and mixture of experts
Weaknesses
- Explanatory text and figures are in the paid book, not in the repo
- Local setup is only a quick-start guide; results may differ by OS and versions
- No tagged releases; README states no pinned package versions
- Not a library or tool, only teaching code
What it needs
- GPU optional
- Needs Google Colab, Jupyter, PyTorch
Also in Learning and cookbooks
See all 14| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on curriculum for building AI systems from math to agents | 82 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | hello-agentsChinese-language course on building LLM agents from scratch | 76 out of 100 |
| #4 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 75 out of 100 |
| #5 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 74 out of 100 |