RLHF -- DPO 本文最后更新于：February 16, 2025 pm RLHF – DPO ongoing AIGC > RLHF #智能系统 #深度学习 #AIGC RLHF -- DPO https://jesseprince.github.io/2025/02/16/aigcs/rlhf/dpo/ Author 林正 Posted on February 16, 2025 Licensed under RLHF -- GRPO Previous RLHF -- From Zero to PPO 代码篇 Next