Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
dhruvdh's favorites
login
submissions
|
comments
1.
Sophia: Scalable Stochastic 2nd-Order Optimizer for Language Model Pre-Training
(
arxiv.org
)
54 points
by
tosh
8 months ago
|
2 comments
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: