Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
brucethemoose2
on Dec 8, 2023
|
parent
|
context
|
favorite
| on:
Mistral "Mixtral" 8x7B 32k model [magnet]
In addition to what was said, if its anything like DPO you don't need a
lot
of data, just a good set. For instance, DPO requires "good" and "bad" responses for each given prompt.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
