Llm Course

<div align="center"> <img src="img/banner.png" alt="LLM Course"> <p align="center"> 𝕏 <a href="https://twitter.com/maximelabonne">Follow me on X</a> • 🤗 <a href="https://huggingface.co/mlabonne">Hugging Face</a> • 💻 <a href="https://mlabonne.github.io/blog">Blog</a> • 📙 <a href="https://packt.link/a/9781836200079">LLM Engineer's Handbook</a> </p> </div> <br/>

<a href="https://a.co/d/a2M67rE"><img align="right" width="25%" src="https://i.imgur.com/7iNjEq2.png" alt="LLM Engineer's Handbook Cover"/></a>The LLM course is divided into three parts:

1. 🧩 LLM Fundamentals is optional and covers fundamental 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.

[!NOTE] Based on this course, I co-wrote the LLM Engineer's Handbook, 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.

For a more comprehensive version of this course, check out the DeepWiki.

📝 Notebooks

A list of notebooks and articles I wrote about LLMs.

<details> <summary>Toggle section (optional)</summary>

Tools

| Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod | <a href="https://colab.research.google.com/drive/1Igs3WZuXAIv9X0vwqiE90QlEPys8e8Oa?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. | <a href="https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. | <a href="https://colab.research.google.com/drive/1TsDKNo2riwVmU55gjuBgB1AXVtRRfRHW?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. | <a href="https://colab.research.google.com/drive/1b6nqC7UZVt8bx4MksX7s656GXPM-eWw4?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 🌳 Model Family Tree | Visualize the family tree of merged models. | <a href="https://colab.research.google.com/drive/1s2eQlolcI1VGgDhqWIANfkfKvcKrMyNr?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. | <a href="https://colab.research.google.com/drive/1LcVUW5wsJTO2NGmozjji5CkC--646LgC"><img src="img/colab.svg" alt="Open In Colab"></a> | | ✂️ AutoAbliteration | Automatically abliteration models with custom datasets. | <a href="https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 🧼 AutoDedup | Automatically deduplicate datasets using the Rensa library. | <a href="https://colab.research.google.com/drive/1o1nzwXWAa8kdkEJljbJFW1VuI-3VZLUn?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> |

Fine-tuning

| Notebook | Description | Article | Notebook | |---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------| | Fine-tune Llama 3.1 with Unsloth | Ultra-efficient supervised fine-tuning in Google Colab. | Article | <a href="https://colab.research.google.com/drive/164cg_O7SV7G8kZr_JXqLd6VC7pd86-1Z?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Fine-tune Llama 3 with ORPO | Cheaper and faster fine-tuning in a single stage with ORPO. | Article | <a href="https://colab.research.google.com/drive/1eHNWg9gnaXErdAa8_mcvjMupbSS6rDvi"><img src="img/colab.svg" alt="Open In Colab"></a> | | Fine-tune Mistral-7b with DPO | Boost the performance of supervised fine-tuned models with DPO. | Article | <a href="https://colab.research.google.com/drive/15iFBr1xWgztXvhrj5I9fBv20c7CFOPBE?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Fine-tune Mistral-7b with QLoRA | Supervised fine-tune Mistral-7b in a free-tier Google Colab with TRL. | | <a href="https://colab.research.google.com/drive/1o_w0KastmEJNVwT5GoqMCciH-18ca5WS?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Fine-tune CodeLlama using Axolotl | End-to-end guide to the state-of-the-art tool for fine-tuning. | Article | <a href="https://colab.research.google.com/drive/1Xu0BrCB7IShwSWKVcfAfhehwjDrDMH5m?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Fine-tune Llama 2 with QLoRA | Step-by-step guide to supervised fine-tune Llama 2 in Google Colab. | Article | <a href="https://colab.research.google.com/drive/1PEQyJO1-f6j0S_XJ8DV50NkpzasXkrzd?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> |

Quantization

| Notebook | Description | Article | Notebook | |---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------| | Introduction to Quantization | Large language model optimization using 8-bit quantization. | Article | <a href="https://colab.research.google.com/drive/1DPr4mUQ92Cc-xf4GgAaB6dFcFnWIvqYi?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | 4-bit Quantization using GPTQ | Quantize your own open-source LLMs to run them on consumer hardware. | Article | <a href="https://colab.research.google.com/drive/1lSvVDaRgqQp_mWK_jC9gydz6_-y6Aq4A?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Quantization with GGUF and llama.cpp | Quantize Llama 2 models with llama.cpp and upload GGUF versions to the HF Hub. | Article | <a href="https://colab.research.google.com/drive/1pL8k7m04mgE5jo2NrjGi8atB0j_37aDD?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | ExLlamaV2: The Fastest Library to Run LLMs | Quantize and run EXL2 models and upload them to the HF Hub. | Article | <a href="https://colab.research.google.com/drive/1yrq4XBlxiA0fALtMoT2dwiACVc77PHou?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> |

Other

| Notebook | Description | Article | Notebook | |---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------| | Merge LLMs with MergeKit | Create your own models easily, no GPU required! | Article | <a href="https://colab.research.google.com/drive/1_JS7JKJAQozD48-LhYdegcuuZ2ddgXfr?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Create MoEs with MergeKit | Combine multiple experts into a single frankenMoE | Article | <a href="https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Uncensor any LLM with abliteration | Fine-tuning without retraining | Article | <a href="https://colab.research.google.com/drive/1VYm3hOcvCpbGiqKZb141gJwjdmmCcVpR?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Improve ChatGPT with Knowledge Graphs | Augment ChatGPT's answers with knowledge graphs. | Article | <a href="https://colab.research.google.com/drive/1mwhOSw9Y9bgEaIFKT4CLi0n18pXRM4cj?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> | | Decoding Strategies in Large Language Models | A guide to text generation from beam search to nucleus sampling | Article | <a href="https://colab.research.google.com/drive/19CJlOS5lI29g-B3dziNn93Enez1yiHk2?usp=sharing"><img src="img/colab.svg" alt="Open In Colab"></a> |

</details>

🧩 LLM Fundamentals

This section introduces essential knowledge about mathematics, Python, and neural networks. You might not want to start here but refer to it as needed.

<details> <summary>Toggle section (optional)</summary>

1. Mathematics for Machine Learning

Before mastering machine learning, it is importa