News for hackers. Stuff that matters.
Re:A Simple Transformer Implementation(PyTorch) Without Diff... by mark_l_watson on Monday January 31, 2022 @10:51AM (#30149313)
I agree, adding generating sequences would be good.

I like projects like this that are short and understandable. Also, some credit to Chenrong Lu for writing the low level code that is used.

Nice!

Re:A Simple Transformer Implementation(PyTorch) Without Diff... by IpsumDominum on Monday January 31, 2022 @04:44PM (#30154903)
Perhaps I'd add a small script with different type of generating functions, thanks for the suggestion.

Me too :) For educational/reference purposes, there's a lot of complexity which can be introduced which is irrelevant to the principles, I hope my code was understandable enough.

Thanks a lot!