gptkbp:instanceOf
|
large language model
|
gptkbp:architecture
|
encoder-decoder
decoder-only
encoder-only
|
gptkbp:author
|
gptkb:Xuezhi_Wang
gptkb:Sebastian_Riedel
gptkb:Ed_H._Chi
gptkb:Donald_Metzler
gptkb:Zhen_Qin
gptkb:Mostafa_Dehghani
gptkb:Colin_Raffel
gptkb:Noam_Shazeer
gptkb:Quoc_V._Le
gptkb:Javier_Gonzalez
gptkb:William_Fedus
Denny Zhou
Orhan Firat
Jason Wei
Hyung Won Chung
Dale Schuurmans
Jianmo Ni
Jinfeng Rao
Vinh Q. Tran
Yi Tay
|
gptkbp:basedOn
|
gptkb:transformation
|
gptkbp:developedBy
|
gptkb:Google_Research
|
gptkbp:fullName
|
Unifying Language Learning
|
https://www.w3.org/2000/01/rdf-schema#label
|
UL2
|
gptkbp:license
|
Apache 2.0
|
gptkbp:notableFor
|
improved generalization across tasks
unifying pretraining objectives
|
gptkbp:notablePublication
|
UL2: Unifying Language Learning Paradigms
https://arxiv.org/abs/2205.05131
|
gptkbp:openSource
|
yes
|
gptkbp:relatedTo
|
gptkb:T5
gptkb:GPT-3
gptkb:BERT
|
gptkbp:releaseYear
|
2022
|
gptkbp:supports
|
few-shot learning
multi-task learning
zero-shot learning
prompt-based learning
|
gptkbp:trainer
|
large-scale text datasets
|
gptkbp:bfsParent
|
gptkb:transformer_(machine_learning_model)
|
gptkbp:bfsLayer
|
6
|