Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
danpalmer
9 months ago
|
parent
|
context
|
favorite
| on:
Attention Wasn't All We Needed
The Llama models are substantially behind the state of the art, particularly when it comes to efficiency, they’re probably not the best example for adoption of these sorts of techniques.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: