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
dnnddidiej
17 hours ago
|
on: Do transformers need three projections? Systematic study of QKV variants
No one got fired for choosing QKV I guess
reply
Hacker News new | past | comments | ask | show | jobs | submit