Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gdiamos
on Feb 8, 2024
|
parent
|
context
|
favorite
| on:
How we got fine-tuning Mistral-7B to not suck
Not literally infinite, but Llama2 scale models can handle about 10 trillion tokens.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
