Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
7e
18 hours ago
|
on: Do transformers need three projections? Systematic study of QKV variants
More evidence that the original Transformer authors didn't really know what they were doing, but they
did
have access to more cheap compute than anyone else.
reply
loading story #48415830