{"data":{"slug":"mlabonne-llm-course","name":"llm-course","tagline":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","github_url":"https://github.com/mlabonne/llm-course","owner":"mlabonne","repo":"llm-course","owner_avatar_url":"https://avatars.githubusercontent.com/u/81252890?v=4","primary_language":null,"stars":81512,"forks":9490,"topics":["course","large-language-models","llm","machine-learning","roadmap"],"archived":false,"github_pushed_at":"2026-02-05T13:09:26+00:00","maintenance_label":"Slowing","stars_delta_30d":771,"url":"https://www.graphcanon.com/tools/mlabonne-llm-course","markdown_url":"https://www.graphcanon.com/tools/mlabonne-llm-course.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mlabonne-llm-course","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mlabonne-llm-course","description":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","homepage_url":"https://mlabonne.github.io/blog/","license":"Apache-2.0","open_issues":86,"watchers":749,"ai_summary":"Provides a guided course on LLMs divided into three parts: fundamentals, building the best possible models using latest techniques, and creating/deploying applications. Includes materials like notebooks for automated evaluation, model merging, fine-tuning in the cloud, and quantization.","readme_excerpt":"
\n\"LLM\n

\n ๐• Follow me on X โ€ข \n ๐Ÿค— Hugging Face โ€ข \n ๐Ÿ’ป Blog โ€ข \n ๐Ÿ“™ LLM Engineer's Handbook\n

\n
\n
\n\n\"LLMThe LLM course is divided into three parts:\n\n1. ๐Ÿงฉ **LLM Fundamentals** is optional and covers fundamental knowledge about mathematics, Python, and neural networks.\n2. ๐Ÿง‘โ€๐Ÿ”ฌ **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques.\n3. ๐Ÿ‘ท **The LLM Engineer** focuses on creating LLM-based applications and deploying them.\n\n> [!NOTE]\n> Based on this course, I co-wrote the [LLM Engineer's Handbook](https://packt.link/a/9781836200079), a hands-on book that covers an end-to-end LLM application from design to deployment. The LLM course will always stay free, but you can support my work by purchasing this book.\n\nFor a more comprehensive version of this course, check out the [DeepWiki](https://deepwiki.com/mlabonne/llm-course/).\n\n## ๐Ÿ“ Notebooks\n\nA list of notebooks and articles I wrote about LLMs.\n\n
\nToggle section (optional)\n\n### Tools\n\n| Notebook | Description | Notebook |\n|----------|-------------|----------|\n| ๐Ÿง [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) | Automatically evaluate your LLMs using RunPod | \"Open |\n| ๐Ÿฅฑ LazyMergekit | Easily merge models using MergeKit in one click. | \"Open |\n| ๐ŸฆŽ LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. | \"Open |\n| โšก AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. | \"Open |\n| ๐ŸŒณ Model Family Tree | Visualize the family tree of merged models. | \"Open |\n| ๐Ÿš€ ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. | \"Open |\n| โœ‚๏ธ AutoAbliteration | Automatically abliteration models with custom datasets. | \"Open |\n| ๐Ÿงผ AutoDedup | Automatically deduplicate datasets using the Rensa library. | \"Open |\n\n### Fine-tuning\n\n| Notebook | Description | Article | Notebook |\n|---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|\n| Fine-tune Llama 3.1 with Unsloth | Ultra-efficient supervised fine-tuning in Google Colab. | [Article](https://mlabonne.github.io/blog/posts/2024-07-29_Finetune_Llama31.html) |