CME 295 - Transformers & Large Language Models

This course explores the world of Transformers and Large Language Models (LLMs). You'll learn the evolution of NLP methods, the core components of the Transformer architecture, along with how they relate to LLMs as well as techniques to enhance model performance for real-world applications. Through a mix of theory and practical insights, this course will equip you with the knowledge to leverage LLMs effectively. Ideal for those with a background in calculus, linear algebra, and basic machine learning concepts.

Syllabus Cheatsheet Ed

Course staff


Afshine Amidi
Instructor

Shervine Amidi
Instructor

Course information

  • Class communication primarily happens on the CME 295 Ed forum.
  • The course content is listed in the syllabus. Please note that for now, slides are only available to enrolled students. We will be publishing public-facing material soon, stay tuned!
  • For general inquiries, please contact cme295-spr2425-staff@lists.stanford.edu.

Class components

CME 295 has the following components:

  • In-person lecture, once a week.
  • Quizz posted on Canvas after each lecture. You will need to submit your answers within a week of the lecture.

Class textbook

Class textbook

Super Study Guide: Transformers & Large Language Models

Available at the Stanford library or online.