Stanford CS336: Language Modeling from Scratch

I was recommended Stanford CS336 (Spring 2026) as a way to learn the fundamentals behind LLMs and get some hands-on experience. This series is where I keep my notes, implementation details, and experiment results to organize my understanding and for future reference.

This class reminds me of a joke from college in 2020:

• Q: “What’s the most important class a CS student should take?”
• A: “Intro to Deep Learning. Not enough to become a deep learning researcher, good enough to know who’s bluffing.”

Posts in This Series

The posts combine lecture notes with the assignments.

1. Building a Transformer Language Model

2. Making Training Efficient

3. Data and Scaling Laws

4. Post-training and Reinforcement Learning

5. Inference and Evaluation