LLM Resources

A running list of courses and materials for learning about large language models. Will keep adding to this as I find more.

Courses

Stanford CS336 — Language Modeling from Scratch

https://cs336.stanford.edu/

Builds a language model end-to-end, the way OS courses build an operating system from scratch: tokenizers, transformer architecture, data collection and cleaning for pre-training, training infrastructure, and evaluation. Probably the best single course for understanding what actually goes into an LLM under the hood. Lecture videos and assignments are public.

CMU 11-711 — Advanced NLP (Spring 2026)

https://cmu-l3.github.io/anlp-spring2026/

CMU’s graduate NLP course, taught by Sean Welleck in Spring 2026. Covers modern NLP with a heavy LLM focus — architectures, training, prompting, evaluation, and current research directions. Course code is public at cmu-l3/anlp-spring2026-code.