Dark Hacker News
new
|
best
|
ask
|
show
|
jobs
redlock | Dark Hacker News
user:
redlock
created:
October 2, 2015
karma:
24
submissions
comments
1.
New deepseek paper: Natively Trainable Sparse Attention mechanism
(twitter.com)
5 points
by
redlock
1 year ago
|
1 comment