MergeDistill: Merging Language Models using Pre-trained Distillation

Simran Khanuja, Melvin Johnson, Partha Talukdar


Anthology ID:
2021.findings-acl.254
Volume:
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
Month:
August
Year:
2021
Address:
Online
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2874–2887
Language:
URL:
https://aclanthology.org/2021.findings-acl.254
DOI:
10.18653/v1/2021.findings-acl.254
Bibkey:
Cite (ACL):
Simran Khanuja, Melvin Johnson, and Partha Talukdar. 2021. MergeDistill: Merging Language Models using Pre-trained Distillation. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2874–2887, Online. Association for Computational Linguistics.
Cite (Informal):
MergeDistill: Merging Language Models using Pre-trained Distillation (Khanuja et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.findings-acl.254.pdf
Video:
 https://preview.aclanthology.org/auto-file-uploads/2021.findings-acl.254.mp4
Data
TyDi QAXQuAD