CH 00 · Start Here: Foundational Modelling, Explained Simply · 04/05
Read as one pageChapter map
- The Transformer: the engine inside every modern model
- Scaling Laws and Chinchilla: how big should a model be?
- Alignment: turning a text predictor into a helpful assistant (RLHF and DPO)
- LoRA: fine-tuning giant models on a budget
- Mixtral and Mixture of Experts: more brain, same speed
- Judging models: how do we measure quality?
- Glossary: every key term, explained from zero
Finished this idea?
Your learning progress stays in this browser.