Cite
Notes
Only stored in your browser.
Attribution
Do Transformer Modifications Transfer Across Implementations and Applications?
EMNLP 2021 11
Merging Models with Fisher-Weighted Averaging
arXiv 2021
from 2 papers
Colin Raffel
Adam Roberts
Hyung Won Chung
researcher
Jake Marcus
Karishma Malkan
Nan Ding
Noah Fiedel
Noam Shazeer
VP / co-lead Gemini
Sharan Narang
Thibault Fevry