Efficient Training of Language Models with Compact and Consistent Next Token Distributions

Efficient Training of Language Models with Compact and Consistent Next Token Distributions Ashutosh Sathe author Sunita Sarawagi author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication sathe-sarawagi-2024-efficient 10.18653/v1/2024.findings-acl.717 https://aclanthology.org/2024.findings-acl.717/ 2024-08 12051 12064