Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/conf/iclr/KomatsuzakiPLRM23
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/conf/iclr/KomatsuzakiPLRM23
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Aran_Komatsuzaki
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Basil_Mustafa
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Carlos_Riquelme_Ruiz
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/James_Lee-Thorp
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Joan_Puigcerver
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Joshua_Ainslie
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Mostafa_Dehghani_0001
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Neil_Houlsby
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yi_Tay
>
foaf:
homepage
<
https://openreview.net/pdf?id=T5nUQDrM4u
>
dc:
identifier
DBLP conf/iclr/KomatsuzakiPLRM23
(xsd:string)
dcterms:
issued
2023
(xsd:gYear)
rdfs:
label
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Aran_Komatsuzaki
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Basil_Mustafa
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Carlos_Riquelme_Ruiz
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/James_Lee-Thorp
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Joan_Puigcerver
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Joshua_Ainslie
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Mostafa_Dehghani_0001
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Neil_Houlsby
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yi_Tay
>
dcterms:
partOf
<
https://dblp.l3s.de/d2r/resource/publications/conf/iclr/2023
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/conf/iclr/KomatsuzakiPLRM23/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/conf/iclr/KomatsuzakiPLRM23
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/conf/iclr/iclr2023.html#KomatsuzakiPLRM23
>
rdfs:
seeAlso
<
https://openreview.net/pdf?id=T5nUQDrM4u
>
swrc:
series
<
https://dblp.l3s.de/d2r/resource/conferences/iclr
>
dc:
title
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:InProceedings
rdf:
type
foaf:Document