ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation

@misc{wu2024realhfoptimizedrlhf,
      title={ReaLHF: Optimized RLHF Training for Large Language Models through Parameter Reallocation}, 
      author={Yi Wu and Huanchen Zhang and Wei Fu and Zhiyu Mei and Guangju Wang and Kaiwei Li},
      year={2024},
      eprint={2406.14088},
      archivePrefix={arXiv},
      primaryClass={cs.DC},
      url={https://arxiv.org/abs/2406.14088}, 
}