Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Eisenstein
6 months ago
|
parent
|
context
|
favorite
| on:
Mistral AI Launches New 8x22B MOE Model
You need to use their beginning and end token scheme and set rep pen to 1 to get good quality out of cr+.
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
