CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code

Nadezhda Chirkova, Sergey Troshin. CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023. [doi]

Abstract

Abstract is missing.