Cite
Notes
Only stored in your browser.
Attribution
ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation
arXiv 2024
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
arXiv 2023
from 2 papers
Huanchen Zhang
Wei Fu
Yi Wu
Zhiyu Mei
Jiaxuan Gao
Kaiwei Li