Best LLM Courses
Large language models deserve their own list: the field moves too fast for generic ML courses to keep up. These are the courses that actually teach how LLMs work and how to build with them — ranked by depth, currency, and teaching quality. Rankings follow our methodology.
- 1
Stanford CS224n — NLP with Deep Learning (Public Materials)
Stanford University
The academic foundation: CS224n takes you from word vectors to transformers with full mathematical rigor, lectures and assignments public. If you want to understand LLMs rather than just use them, start here.
Read the full review → - 2
Generative AI with Large Language Models (DeepLearning.AI + AWS)
DeepLearning.AI
The best structured practitioner course: DeepLearning.AI and AWS cover the full LLM lifecycle — pre-training, fine-tuning, RLHF, deployment — in about sixteen hours. Practitioner depth without academic prerequisites.
Read the full review → - 3
Hugging Face LLM Course
Hugging Face
The free, code-first alternative: Hugging Face's course teaches the transformer stack by having you use it — tokenizers, fine-tuning, the Hub. Free and continuously maintained.
Read the full review → - 4
Hung-yi Lee's Machine Learning / Generative AI Lectures
National Taiwan University (NTU) — Prof. Hung-yi Lee
The best Chinese-language option: Professor Hung-yi Lee's generative AI lectures explain LLM mechanics with unusual clarity and humor. Free on YouTube and Bilibili.
Read the full review →