News for hackers. Stuff that matters.
Re:You probably don’t need to fine-tune LLMs by clharman on Friday August 18, 2023 @08:28PM (#37184061)
@rafaelero I'm working on a blogpost (https://colinharman.substack.com/) to demonstrate this fact since I get a lot of tiresome questions like "why don't you just train instead of retrieving"

Do you have any scripts you could share for the training/eval process? Would love to credit you in the post

There are no comments on this comment yet.