1 result found Sort:

sail-sg
oat sail-sg
6
107
apache-2.0
5
🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
dpo llm rlhf alignment online-rl reasoning llm-aligment distributed-rl dueling-bandits llm-exploration online-alignment thompson-sampling distributed-training
Created 2024-10-15
26 commits to main branch, last one 13 hours ago