foundation-model ·
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
𝕏 Follow me on X • 🤗 Hugging Face • 💻 Blog • 📙 LLM Engineer's Handbook
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](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.
For a more comprehensive version of this course, check out the [DeepWiki](https://deepwiki.com/mlabonne/llm-course/).
## 📝 Notebooks
A list of notebooks and articles I wrote about LLMs.
Toggle section (optional)
### Tools
| Notebook | Description | Notebook |
|----------|-------------|----------|
| 🧐 [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) | Automatically evaluate your LLMs using RunPod | 
|
| 🥱 LazyMergekit | Easily merge models using MergeKit in one click. | |
| 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. | |
| ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. | |
| 🌳 Model Family Tree | Visualize the family tree of merged models. | |
| 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. | |
| ✂️ AutoAbliteration | Automatically abliteration models with custom datasets. | |
| 🧼 AutoDedup | Automatically deduplicate datasets using the Rensa library. | |
### Fine-tuning
| Notebook | Description | Article | Notebook |
|---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|
| 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) | |
| Fine-tune Llama 3 with ORPO | Cheaper and faster fine-tuning in a single stage with ORPO. | [Article](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) | |
| Fine-tune Mistral-7b with DPO | Boost the performance of supervised fine-tuned models with DPO. | [Article](https://mlabonne.github.io/blog/posts/Fine_tune_Mistral_7b_with_DPO.html) | |
| Fine-tune Mistral-7b with QLoRA | Supervised fine-tune Mistral-7b in a free-tier Google Colab with TRL. | | |
| Fine-tune CodeLlama using Axolotl | End-to-end guide to the state-of-the-art tool for fine-tuning. | [Article](https://mlabonne.github.io/blog/posts/A_Beginners_Guide_to_LLM_Finetuning.html) | |
| Fine-tune Llama 2 with QLoRA | Step-by-step guide to supervised fine-tune Llama 2 in Google Colab. | [Article](https://mlabonne.github.io/blog/posts/Fine_Tune_Your_Own_Llama_2_Model_in_a_Colab_Notebook.html) | |
### Quantization
| Notebook | Description | Article | Notebook |
|---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|
| Introduction to Quantization | Large language model optimization using 8-bit quantization. | [Article](https://mlabonne.github.io/blog/posts/Introduction_to_Weight_Quantization.html) | |
| 4-bit Quantization using GPTQ | Quantize your own open-source LLMs to run them on consumer hardware. | [Article](https://mlabonne.github.io/blog/4bit_quantization/) | |
| Quantization with GGUF and llama.cpp | Quantize Llama 2 models with llama.cpp and upload GGUF versions to the HF Hub. | [Article](https://mlabonne.github.io/blog/posts/Quantize_Llama_2_models_using_ggml.html) | |
| ExLlamaV2: The Fastest Library to Run LLMs | Quantize and run EXL2 models and upload them to the HF Hub. | [Article](https://mlabonne.github.io/blog/posts/ExLlamaV2_The_Fastest_Library_to_Run%C2%A0LLMs.html) | |
### Other
| Notebook | Description | Article | Notebook |
|---------------------------------------|-------------------------------------------------------------------------|---------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|
| Merge LLMs with MergeKit | Create your own models easily, no GPU required! | [Article](https://mlabonne.github.io/blog/posts/2024-01-08_Merge_LLMs_with_mergekit%20copy.html) | |
| Create MoEs with MergeKit | Combine multiple experts into a single frankenMoE | [Article](https://mlabonne.github.io/blog/posts/2024-03-28_Create_Mixture_of_Experts_with_MergeKit.html) | |
| Uncensor any LLM with abliteration | Fine-tuning without retraining | [Article](https://mlabonne.github.io/blog/posts/2024-06-04_Uncensor_any_LLM_with_abliteration.html) | |
| Improve ChatGPT with Knowledge Graphs | Augment ChatGPT's answers with knowledge graphs. | [Article](https://mlabonne.github.io/blog/posts/Article_Improve_ChatGPT_with_Knowledge_Graphs.html) | |
| Decoding Strategies in Large Language Models | A guide to text generation from beam search to nucleus sampling | [Article](https://mlabonne.github.io/blog/posts/2022-06-07-Decoding_strategies.html) | |
## 🧩 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.
Toggle section (optional)
### 1. Mathematics for Machine Learning
Before mastering machine learning, it is important to understand the fundamental mathematical concepts that power these algorithms.
- **Linear Algebra**: This is crucial for understanding many algorithms, especially those used in deep learning. Key concepts include vectors, matrices, determinants, eigenvalues and eigenvectors, vector spaces, and linear transformations.
- **Calculus**: Many machine learning algorithms involve the optimization of continuous functions, which requires an understanding of derivatives, integrals, limits, and series. Multivariable calculus and the concept of gradients are also important.
- **Probability and Statistics**: These are crucial for understanding how models learn from data and make predictions. Key concepts include probability theory, random variables, probability distributions, expectations, variance, covariance, correlation, hypothesis testing, confidence intervals, maximum likelihood estimation, and Bayesian inference.
📚 Resources:
- [3Blue1Brown - The Essence of Linear Algebra](https://www.youtube.com/watch?v=fNk_zzaMoSs&list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab): Series of videos that give a geometric intuition to these concepts.
- [StatQuest with Josh Starmer - Statistics Fundamentals](https://www.youtube.com/watch?v=qBigTkBLU6g&list=PLblh5JKOoLUK0FLuzwntyYI10UQFUhsY9): Offers simple and clear explanations for many statistical concepts.
- [Seeing Theory](https://seeing-theory.brown.edu/): A visual introduction to probability and statistics from Brown University.
- [Immersive Linear Algebra](https://immersivemath.com/ila/learnmore.html): Another visual interpretation of linear algebra.
- [Khan Academy - Linear Algebra](https://www.khanacademy.org/math/linear-algebra): Great for beginners as it explains the concepts in a very intuitive way.
- [Khan Academy - Calculus](https://www.khanacademy.org/math/calculus-1): An interactive course that covers all the basics of calculus.
- [Khan Academy - Probability and Statistics](https://www.khanacademy.org/math/statistics-probability): Delivers the material in an easy-to-understand format.
---
### 2. Python for Machine Learning
Python is a powerful and flexible programming language that's particularly good for machine learning, thanks to its readability, consistency, and robust ecosystem of data science libraries.
- **Python Basics**: Python programming requires a good understanding of the basic syntax, data types, error handling, and object-oriented programming.
- **Data Science Libraries**: It includes familiarity with NumPy for numerical operations, Pandas for data manipulation and analysis, Matplotlib and Seaborn for data visualization.
- **Data Preprocessing**: This involves feature scaling and normalization, handling missing data, outlier detection, categorical data encoding, and splitting data into training, validation, and test sets.
- **Machine Learning Libraries**: Proficiency with Scikit-learn, a library providing a wide selection of supervised and unsupervised learning algorithms, is vital. Understanding how to implement algorithms like linear regression, logistic regression, decision trees, random forests, k-nearest neighbors (K-NN), and K-means clustering is important. Dimensionality reduction techniques like PCA and t-SNE are also helpful for visualizing high-dimensional data.
📚 Resources:
- [Real Python](https://realpython.com/): A comprehensive resource with articles and tutorials for both beginner and advanced Python concepts.
- [freeCodeCamp - Learn Python](https://www.youtube.com/watch?v=rfscVS0vtbw): Long video that provides a full introduction into all of the core concepts in Python.
- [Python Data Science Handbook](https://jakevdp.github.io/PythonDataScienceHandbook/): Free digital book that is a great resource for learning pandas, NumPy, Matplotlib, and Seaborn.
- [freeCodeCamp - Machine Learning for Everybody](https://youtu.be/i_LwzRVP7bg): Practical introduction to different machine learning algorithms for beginners.
- [Udacity - Intro to Machine Learning](https://www.udacity.com/course/intro-to-machine-learning--ud120): Free course that covers PCA and several other machine learning concepts.
---
### 3. Neural Networks
Neural networks are a fundamental part of many machine learning models, particularly in the realm of deep learning. To utilize them effectively, a comprehensive understanding of their design and mechanics is essential.
- **Fundamentals**: This includes understanding the structure of a neural network, such as layers, weights, biases, and activation functions (sigmoid, tanh, ReLU, etc.)
- **Training and Optimization**: Familiarize yourself with backpropagation and different types of loss functions, like Mean Squared Error (MSE) and Cross-Entropy. Understand various optimization algorithms like Gradient Descent, Stochastic Gradient Descent, RMSprop, and Adam.
- **Overfitting**: Understand the concept of overfitting (where a model performs well on training data but poorly on unseen data) and learn various regularization techniques (dropout, L1/L2 regularization, early stopping, data augmentation) to prevent it.
- **Implement a Multilayer Perceptron (MLP)**: Build an MLP, also known as a fully connected network, using PyTorch.
📚 Resources:
- [3Blue1Brown - But what is a Neural Network?](https://www.youtube.com/watch?v=aircAruvnKk): This video gives an intuitive explanation of neural networks and their inner workings.
- [freeCodeCamp - Deep Learning Crash Course](https://www.youtube.com/watch?v=VyWAvY2CF9c): This video efficiently introduces all the most important concepts in deep learning.
- [Fast.ai - Practical Deep Learning](https://course.fast.ai/): Free course designed for people with coding experience who want to learn about deep learning.
- [Patrick Loeber - PyTorch Tutorials](https://www.youtube.com/playlist?list=PLqnslRFeH2UrcDBWF5mfPGpqQDSta6VK4): Series of videos for complete beginners to learn about PyTorch.
---
### 4. Natural Language Processing (NLP)
NLP is a fascinating branch of artificial intelligence that bridges the gap between human language and machine understanding. From simple text processing to understanding linguistic nuances, NLP plays a crucial role in many applications like translation, sentiment analysis, chatbots, and much more.
- **Text Preprocessing**: Learn various text preprocessing steps like tokenization (splitting text into words or sentences), stemming (reducing words to their root form), lemmatization (similar to stemming but considers the context), stop word removal, etc.
- **Feature Extraction Techniques**: Become familiar with techniques to convert text data into a format that can be understood by machine learning algorithms. Key methods include Bag-of-words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), and n-grams.
- **Word Embeddings**: Word embeddings are a type of word representation that allows words with similar meanings to have similar representations. Key methods include Word2Vec, GloVe, and FastText.
- **Recurrent Neural Networks (RNNs)**: Understand the working of RNNs, a type of neural network designed to work with sequence data. Explore LSTMs and GRUs, two RNN variants that are capable of learning long-term dependencies.
📚 Resources:
- [Lena Voita - Word Embeddings](https://lena-voita.github.io/nlp_course/word_embeddings.html): Beginner-friendly course about concepts related to word embeddings.
- [RealPython - NLP with spaCy in Python](https://realpython.com/natural-language-processing-spacy-python/): Exhaustive guide about the spaCy library for NLP tasks in Python.
- [Kaggle - NLP Guide](https://www.kaggle.com/learn-guide/natural-language-processing): A few notebooks and resources for a hands-on explanation of NLP in Python.
- [Jay Alammar - The Illustration Word2Vec](https://jalammar.github.io/illustrated-word2vec/): A good reference to understand the famous Word2Vec architecture.
- [Jake Tae - PyTorch RNN from Scratch](https://jaketae.github.io/study/pytorch-rnn/): Practical and simple implementation of RNN, LSTM, and GRU models in PyTorch.
- [colah's blog - Understanding LSTM Networks](https://colah.github.io/posts/2015-08-Understanding-LSTMs/): A more theoretical article about the LSTM network.
## 🧑🔬 The LLM Scientist
This section of the course focuses on learning how to build the best possible LLMs using the latest techniques.
### 1. The LLM Architecture
An in-depth knowledge of the Transformer architecture is not required, but it's important to understand the main steps of modern LLMs: converting text into numbers through tokenization, processing these tokens through layers including attention mechanisms, and finally generating new text through various sampling strategies.
- **Architectural overview**: Understand the evolution from encoder-decoder Transformers to decoder-only architectures like GPT, which form the basis of modern LLMs. Focus on how these models process and generate text at a high level.
- **Tokenization**: Learn the principles of tokenization - how text is converted into numerical representations that LLMs can process. Explore different tokenization strategies and their impact on model performance and output quality.
- **Attention mechanisms**: Master the core concepts of attention mechanisms, particularly self-attention and its variants. Understand how these mechanisms enable LLMs to process long-range dependencies and maintain context throughout sequences.
- **Sampling techniques**: Explore various text generation approaches an