Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rolisz
on Aug 18, 2023
|
parent
|
context
|
favorite
| on:
You probably don’t need to fine-tune an LLM
I don't think so. You don't have enough data for finetuning. How would you even fine tune? If you have less then several thousand examples, I wouldn't even think about finetuning
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: