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
xiaoyu2006
21 hours ago
|
on: Do transformers need three projections? Systematic study of QKV variants
Will be great and amusing if it actually turns out that we have been doing transformer overly-complex. The code repo is missing tho...
reply
ares623
20 hours ago
|
parent
Gets the juices flowing though..
reply