[storus]

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

[nafizh]

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

[storus]

It's also covered by CS329H.

[upbeat_general]

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