A free, MIT-licensed course of 542 lessons that builds AI engineering concepts from scratch in Python, TypeScript, Rust and Julia.
71.4K12.6KPythonMITUpdated 2 days ago
peremartra/Large-Language-Model-Notebooks-Course
A free hands-on course with Jupyter notebooks and articles covering LLM applications with OpenAI, Hugging Face, LangChain, vector databases, fine-tuning and pruning.
- Stars
- 1,825
- Forks
- 450
- Open issues
- 0
- Last commit
- 22 days ago
What is it?
This repository is a free, hands-on course about Large Language Models, organized as Jupyter notebooks hosted mostly on Colab, each paired with a longer article explaining the code. It is the unofficial companion to a book published by Apress, though the course does not contain all of the book's material, and it is still being updated with new lessons.
The course is split into three sections: techniques and libraries, practical projects, and enterprise solutions. The first covers chatbots built on the OpenAI API, natural-language-to-SQL translation, vector databases with ChromaDB, retrieval-augmented generation with LangChain, agents, evaluation metrics such as BLEU and ROUGE, and fine-tuning with PEFT, LoRA and QLoRA. A later part focuses on structured pruning of Llama-family models, attention bypass, knowledge distillation and bias analysis.
Lessons are designed to be followed alongside the article, and some notebooks need more memory than the free Colab tier provides.
Key features
- 01Notebooks cover OpenAI API chatbots, NL-to-SQL and prompt engineering.
- 02Includes RAG pipelines using ChromaDB and LangChain.
- 03Covers evaluation with BLEU, ROUGE, LangSmith and Giskard.
- 04Teaches parameter-efficient fine-tuning with PEFT, LoRA and QLoRA.
- 05Demonstrates pruning and knowledge distillation on Llama 3.2 models.
Use cases
- Learning how to build RAG chatbots with LangChain and a vector database.
- Practicing LLM fine-tuning on a single consumer GPU with QLoRA.
- Exploring model compression techniques such as pruning and distillation.
Quick start
- 1
Open the course notebooks on Google Colab or run them locally from the repository
- 2
Clone the repository
- 3
Read the lesson article alongside the notebook and follow along
Things to know
- Many notebooks use OpenAI or Hugging Face models that need an API key or more memory than the free Colab tier.
- The course is still in permanent development, so lessons are added over time.
- Some lessons are work in progress and have no article yet.
Topics
FAQ
- What is Large-Language-Model-Notebooks-Course?
- A free hands-on course with Jupyter notebooks and articles covering LLM applications with OpenAI, Hugging Face, LangChain, vector databases, fine-tuning and pruning. This repository is a free, hands-on course about Large Language Models, organized as Jupyter notebooks hosted mostly on Colab, each paired with a longer article explaining the code. It is the unofficial companion to a book published by Apress, though the course does not contain all of the book's material, and it is still being updated with new lessons.
- Is Large-Language-Model-Notebooks-Course free to use? What license does it have?
- Large-Language-Model-Notebooks-Course is open source under the MIT license. Check the license terms before using it in commercial products.
- Is Large-Language-Model-Notebooks-Course still maintained?
- Actively maintained. The last commit to Large-Language-Model-Notebooks-Course was on Sep 29, 2026.
- What can I use Large-Language-Model-Notebooks-Course for?
- Learning how to build RAG chatbots with LangChain and a vector database. Practicing LLM fine-tuning on a single consumer GPU with QLoRA. Exploring model compression techniques such as pruning and distillation.
- How do I install Large-Language-Model-Notebooks-Course?
- Open the course notebooks on Google Colab or run them locally from the repository Clone the repository Read the lesson article alongside the notebook and follow along
- Where can I get Large-Language-Model-Notebooks-Course?
- The source code and installation instructions are on GitHub: https://github.com/peremartra/Large-Language-Model-Notebooks-Course
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Chinese-language open tutorial that teaches LLM principles by building a small LLaMA2-style model from scratch, covering Transformer, pretraining, fine-tuning, RAG and agents.
34.5K3.3KJupyter NotebookOtherUpdated 2 months ago
A Chinese-language tutorial collection for deploying, using and fine-tuning open-source LLMs and multimodal models on Linux, with full, LoRA and P-tuning guides.
32.5K3.1KJupyter NotebookApache-2.0Updated last month
A from-scratch PyTorch walkthrough and codebase for training a transformer LLM, covering pretraining, SFT, reward modeling, DPO/PPO/GRPO and generation.
12.3K1.8KPythonMITUpdated 19 days ago
A curated, category-wise list of 120+ open-source libraries for building, training, serving, evaluating and monitoring LLM applications.
10.9K1.7KApache-2.0Updated 10 days ago
A Chinese-language step-by-step guide and demo code for learning LLMs, from calling APIs to local deployment and fine-tuning, with Kaggle/Colab versions.
4.7K489PythonMITUpdated 9 days ago