倉庫議題
kyegomez/Stable-Alignment
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
議題
此倉庫沒有已索引議題。
倉庫議題
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
此倉庫沒有已索引議題。