Re:Let's build GPT: from scratch, in code, spelled out by An...
by ironrabbit on Tuesday January 17, 2023 @08:57PM
(#34422475)
Andrej's "Building Makemore" series is exactly this, it includes a wonderful lecture where he computes all the gradients for a simple network by hand and compares them against the values produced by torch's autograd.
[ Parent
| on HN ]