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.
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.
check out cs 336 stanford, they cover DPO/GRPO and relevant parts needed to train LLMs.
It's also covered by CS329H.
I can assure you that lacking knowledge in DPO (and especially GRPO it’s just stripped down PPO) is not a dealbreaker.