Hi.

In this series, we will study the fundamentals of Large Language Models (LLM) which have taken the world by storm. I believe it is still important for machine learning practitioners to understand how these models work internally, so we can debug and further improve these models. We will start from how we can represent texts (i.e., text embedding), early language models such as Seq2Seq, attention mechanism, to transformers, and more recent state of the arts language models.

If you have any other questions or suggestions, do not hesitate to send me an email to reywiyatno@gmail.com.

Next: Word Embeddings