"GKD: Generalized Knowledge Distillation for Auto-regressive Sequence Models."

Rishabh Agarwal et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2306.13649

access: open

type: Informal or Other Publication

metadata version: 2023-06-27

a service of  Schloss Dagstuhl - Leibniz Center for Informatics