Efficient GPT Model Pre-training using Tensor Train Matrix Representation
Viktoriia Chekalina, Georgiy Novikov, Julia Gusak, Alexander Panchenko, Ivan Oseledets
- Anthology ID:
- 2023.paclic-1.60
- Volume:
- Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation
- Month:
- December
- Year:
- 2023
- Address:
- Hong Kong, China
- Editors:
- Chu-Ren Huang, Yasunari Harada, Jong-Bok Kim, Si Chen, Yu-Yin Hsu, Emmanuele Chersoni, Pranav A, Winnie Huiheng Zeng, Bo Peng, Yuxi Li, Junlin Li
- Venue:
- PACLIC
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 600–608
- Language:
- URL:
- https://aclanthology.org/2023.paclic-1.60
- DOI:
- Bibkey:
- Cite (ACL):
- Viktoriia Chekalina, Georgiy Novikov, Julia Gusak, Alexander Panchenko, and Ivan Oseledets. 2023. Efficient GPT Model Pre-training using Tensor Train Matrix Representation. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 600–608, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Efficient GPT Model Pre-training using Tensor Train Matrix Representation (Chekalina et al., PACLIC 2023)
- Copy Citation:
- PDF:
- https://aclanthology.org/2023.paclic-1.60.pdf
Export citation
@inproceedings{chekalina-etal-2023-efficient,
title = "Efficient {GPT} Model Pre-training using Tensor Train Matrix Representation",
author = "Chekalina, Viktoriia and
Novikov, Georgiy and
Gusak, Julia and
Panchenko, Alexander and
Oseledets, Ivan",
editor = "Huang, Chu-Ren and
Harada, Yasunari and
Kim, Jong-Bok and
Chen, Si and
Hsu, Yu-Yin and
Chersoni, Emmanuele and
A, Pranav and
Zeng, Winnie Huiheng and
Peng, Bo and
Li, Yuxi and
Li, Junlin",
booktitle = "Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation",
month = dec,
year = "2023",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.paclic-1.60",
pages = "600--608",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chekalina-etal-2023-efficient">
<titleInfo>
<title>Efficient GPT Model Pre-training using Tensor Train Matrix Representation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viktoriia</namePart>
<namePart type="family">Chekalina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgiy</namePart>
<namePart type="family">Novikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Gusak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Oseledets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasunari</namePart>
<namePart type="family">Harada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong-Bok</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Si</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Yin</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuele</namePart>
<namePart type="family">Chersoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">A</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winnie</namePart>
<namePart type="given">Huiheng</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junlin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<identifier type="citekey">chekalina-etal-2023-efficient</identifier>
<location>
<url>https://aclanthology.org/2023.paclic-1.60</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>600</start>
<end>608</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings %T Efficient GPT Model Pre-training using Tensor Train Matrix Representation %A Chekalina, Viktoriia %A Novikov, Georgiy %A Gusak, Julia %A Panchenko, Alexander %A Oseledets, Ivan %Y Huang, Chu-Ren %Y Harada, Yasunari %Y Kim, Jong-Bok %Y Chen, Si %Y Hsu, Yu-Yin %Y Chersoni, Emmanuele %Y A, Pranav %Y Zeng, Winnie Huiheng %Y Peng, Bo %Y Li, Yuxi %Y Li, Junlin %S Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation %D 2023 %8 December %I Association for Computational Linguistics %C Hong Kong, China %F chekalina-etal-2023-efficient %U https://aclanthology.org/2023.paclic-1.60 %P 600-608
Markdown (Informal)
[Efficient GPT Model Pre-training using Tensor Train Matrix Representation](https://aclanthology.org/2023.paclic-1.60) (Chekalina et al., PACLIC 2023)
- Efficient GPT Model Pre-training using Tensor Train Matrix Representation (Chekalina et al., PACLIC 2023)
ACL
- Viktoriia Chekalina, Georgiy Novikov, Julia Gusak, Alexander Panchenko, and Ivan Oseledets. 2023. Efficient GPT Model Pre-training using Tensor Train Matrix Representation. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 600–608, Hong Kong, China. Association for Computational Linguistics.