Léo Martin
leo-mart
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset 1 day ago
yitingxie/rlhf-reward-datasets liked a dataset 1 day ago
kunishou/hh-rlhf-49k-ja liked a model 1 day ago
kaiokendev/superhot-30b-8k-no-rlhf-testOrganizations
None yet