gptkbp:instanceOf
|
large language model
|
gptkbp:architecture
|
gptkb:Mixture_of_Experts
|
gptkbp:author
|
gptkb:Jacob_Devlin
gptkb:Adam_Roberts
gptkb:Aakanksha_Chowdhery
gptkb:Gaurav_Mishra
gptkb:Maarten_Bosma
gptkb:Jeff_Dean
gptkb:Zoubin_Ghahramani
gptkb:Katherine_Lee
gptkb:Noam_Shazeer
gptkb:Sharan_Narang
gptkb:Quoc_V._Le
gptkb:Sanket_Vaibhav_Mehta
gptkb:Yonghui_Wu
gptkb:Zhifeng_Chen
|
gptkbp:citation
|
2021
|
gptkbp:developedBy
|
gptkb:Google
|
gptkbp:fullName
|
Generalist Language Model
|
https://www.w3.org/2000/01/rdf-schema#label
|
GLaM
|
gptkbp:language
|
English
|
gptkbp:notableFor
|
scaling language models efficiently
improving efficiency over dense models
using sparse activation
|
gptkbp:notablePublication
|
https://arxiv.org/abs/2112.06905
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
|
gptkbp:parameter
|
1.2 trillion
|
gptkbp:releaseYear
|
2021
|
gptkbp:uses
|
natural language processing
question answering
text generation
language understanding
|
gptkbp:bfsParent
|
gptkb:Switch_Transformer
gptkb:Mixture_of_Experts
gptkb:MoE_Transformer
|
gptkbp:bfsLayer
|
6
|