Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library

Comment by storus

3 days ago

Those don't have DPO/GRPO which arguably made some parts of RL obsolete.

3 comments

storus

Reply

nafizh  3 days ago

check out cs 336 stanford, they cover DPO/GRPO and relevant parts needed to train LLMs.

  • storus  3 days ago

    It's also covered by CS329H.

upbeat_general  3 days ago

I can assure you that lacking knowledge in DPO (and especially GRPO it’s just stripped down PPO) is not a dealbreaker.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities