Transformers, Simply Explained

Transformers are the most widespread architecture used for NLP tasks today, from text generation to summarization to translation to classification and more.

In this post, I explain how transformers work, at a high level view and without any mathematics, so you can gain a general idea of their workings.

You can read it here:

If you have any comments, questions, suggestions, feedback, criticisms, or corrections, please do let me know!

2 Likes