Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
GaggiX
on April 10, 2024
|
parent
|
context
|
favorite
| on:
Implementation of Google's Griffin Architecture – ...
The paper shows that the speed is comparable to transformer models, faster with smaller with "long" sequence length like 8k.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
