仓库议题
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".
议题
此仓库没有已关闭的已索引议题。
仓库议题
Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
此仓库没有已关闭的已索引议题。