Weight subcloning: direct initialization of transformers using larger pretrained ones.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/journals/corr/abs-2312-09299
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/journals/corr/abs-2312-09299
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Devang_Naik
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Fartash_Faghri
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Mehrdad_Farajtabar
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Mohammad_Rastegari
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Mohammad_Samragh
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Oncel_Tuzel
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Raviteja_Vemulapalli
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Sachin_Mehta
>
foaf:
homepage
<
http://dx.doi.org/doi.org%2F10.48550%2FarXiv.2312.09299
>
foaf:
homepage
<
https://doi.org/10.48550/arXiv.2312.09299
>
dc:
identifier
DBLP journals/corr/abs-2312-09299
(xsd:string)
dc:
identifier
DOI doi.org%2F10.48550%2FarXiv.2312.09299
(xsd:string)
dcterms:
issued
2023
(xsd:gYear)
swrc:
journal
<
https://dblp.l3s.de/d2r/resource/journals/corr
>
rdfs:
label
Weight subcloning: direct initialization of transformers using larger pretrained ones.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Devang_Naik
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Fartash_Faghri
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Mehrdad_Farajtabar
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Mohammad_Rastegari
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Mohammad_Samragh
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Oncel_Tuzel
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Raviteja_Vemulapalli
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Sachin_Mehta
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/journals/corr/abs-2312-09299/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/journals/corr/abs-2312-09299
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/journals/corr/corr2312.html#abs-2312-09299
>
rdfs:
seeAlso
<
https://doi.org/10.48550/arXiv.2312.09299
>
dc:
title
Weight subcloning: direct initialization of transformers using larger pretrained ones.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:Article
rdf:
type
foaf:Document
swrc:
volume
abs/2312.09299
(xsd:string)