Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
elcomet
on Dec 8, 2023
|
parent
|
context
|
favorite
| on:
Mistral "Mixtral" 8x7B 32k model [magnet]
We can only compare specific training procedures though.
With a 7b and a 70b trained the same way, the 70b should always be better
nabakin
on Dec 9, 2023
[–]
Makes sense
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
With a 7b and a 70b trained the same way, the 70b should always be better