I am working on a video lecture series that will step through it and "spell it out". Without it even this code can be a bit opaque for someone who is new to the field and e.g. uncomfortable with n-dimensional array manipulations or the surrounding language modeling concepts.

That's very generous of you. Thanks.

All we need now is a good, local copilot implementation. Has anyone done anything like that with minGPT that you know of? Something to inspire the masses like stable diffusion has with images.