ModelsBuildersMulti-source10:36Chinese contentThom Wolf 称开源高质量 RL 环境是当前推动开源前沿最有影响力之举Thom Wolf 点名的一套开源 RL 环境要来了,附约 7k 训练数据和框架,还练出 Artificial Analysis 前六的模型,做 RL 的可以蹲一下。#Thom Wolf#Elie Bakouch#RLVR#reinforcement learning5 sourcesEventThomas Wolf@Thom_WolfSourceRead laterReadWorth followingUsefulFollow Thom Wolf