Sign in

Emergent Modularity in Pre-trained Transformers.

Zhengyan ZhangZhiyuan ZengYankai LinChaojun XiaoXiaozhi WangXu HanZhiyuan LiuRuobing XieMaosong SunJie Zhou
Published in: CoRR (2023)
Keyphrases
  • pre trained
  • training data
  • training examples
  • control signals
  • decision trees
  • wide range
  • appearance variations