Léo Martin's picture

Léo Martin

leo-mart
13 9

AI & ML interests

Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL

Recent Activity

liked a model about 19 hours ago
Ablustrund/moss-rlhf-reward-model-7B-zh
liked a model about 19 hours ago
RLHFlow/pair-preference-model-LLaMA3-8B
liked a model about 19 hours ago
kaiokendev/superhot-13b-8k-no-rlhf-test
View all activity

Organizations

None yet