Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ianpurton
on May 3, 2023
|
parent
|
context
|
favorite
| on:
OpenLLaMA: An Open Reproduction of LLaMA
> We are currently focused on completing the training process on the entire RedPajama dataset.
So that's 1.2 trillion tokens. Nice.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
So that's 1.2 trillion tokens. Nice.