[ford]

Jay Alammar has my favorite sequence of tutorials from basic neural network math to GPT2.

Particularly [0], [1], and [2]

[0] http://jalammar.github.io/illustrated-transformer/

[1] http://jalammar.github.io/illustrated-gpt2/

[2] https://jalammar.github.io/visualizing-neural-machine-transl...