I’ve tried many times to study how LLMs work and how to train them. But every time, the same thing happens — after a few days, I can’t finish the course. Recently, I started a course called:
“A deep understanding of AI large language model mechanisms.” // Build and train LLM NLP transformers and attention mechanisms (PyTorch). Explore with mechanistic interpretability tools.”
The author of this course is Mike X. Cohen. I started it but stopped again after progressing a little bit.
This time, I want to write blog posts based on what I learn so I can keep myself accountable. A big problem with self-study is accountability — since no one is supervising you, most courses never get completed. And if I start teaching someone else, according to Richard Feynman’s method, it will help me learn even better. Let’s see if this time I can actually finish the course.