How LLMs Work
Machine learningA concise and complete study on how large language models work. We will build a small LLM from scratch, explaining the theory first and then implementing it in code.
3 chapters | 13 lessons
Chapters
ML fundamentals
Build the mathematical formulation of a spam filtering model with a simple neural network.
- ML Model
- Evaluation
- Logistic regression
- Training
- Neural Networks
LLMs
Extend the model, turning it into an LLM that generates text.
- Next word prediction
- Embeddings
- Transformers
Implementation
Write a complete implementation for our model in Python.
- Overview
- Helpers
- Modules
- Architecture