MergeDistill: Merging Language Models using Pre-trained Distillation

Autor:	Simran Khanuja, Partha Pratim Talukdar, Melvin Johnson
Rok vydání:	2021
Předmět:	Computer science law business.industry Language model Artificial intelligence computer.software_genre business computer Distillation Natural language processing law.invention
Zdroj:	ACL/IJCNLP (Findings)
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::24572dc900e6ad8a06127be10a407fc5 https://doi.org/10.18653/v1/2021.findings-acl.254 Zobrazit plný text záznamu