|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:architecture
|
encoder-only
|
|
gptkbp:author
|
gptkb:Myle_Ott
gptkb:Marc'Aurelio_Ranzato
gptkb:Alexis_Conneau
gptkb:Luke_Zettlemoyer
gptkb:Guillaume_Lample
gptkb:Naman_Goyal
Vasudev Gupta
|
|
gptkbp:availableOn
|
gptkb:Hugging_Face_Model_Hub
|
|
gptkbp:basedOn
|
gptkb:BERT
gptkb:RoBERTa
|
|
gptkbp:citation
|
2019
|
|
gptkbp:developedBy
|
gptkb:Facebook_AI
|
|
gptkbp:github
|
https://github.com/pytorch/fairseq/tree/main/examples/xlmr
|
|
gptkbp:hasVariant
|
XLM-RoBERTa-base
XLM-RoBERTa-large
|
|
gptkbp:hiddenSize
|
768
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
XLM-RoBERTa
|
|
gptkbp:improves
|
gptkb:mBERT
gptkb:XLM
|
|
gptkbp:input
|
gptkb:text
|
|
gptkbp:language
|
100
|
|
gptkbp:level
|
12
|
|
gptkbp:license
|
gptkb:MIT_License
|
|
gptkbp:maxSequenceLength
|
512
|
|
gptkbp:notablePublication
|
gptkb:Unsupervised_Cross-lingual_Representation_Learning_at_Scale
|
|
gptkbp:numberOfAttentionHeads
|
12
|
|
gptkbp:openSource
|
true
|
|
gptkbp:pretrainingObjective
|
masked language modeling
|
|
gptkbp:publishedIn
|
gptkb:arXiv
|
|
gptkbp:releaseYear
|
2019
|
|
gptkbp:supportsLanguage
|
multilingual
|
|
gptkbp:tokenizerType
|
gptkb:Byte-Pair_Encoding
|
|
gptkbp:trainer
|
gptkb:CommonCrawl
gptkb:Wikipedia
|
|
gptkbp:type
|
gptkb:model
|
|
gptkbp:usedFor
|
machine translation
question answering
natural language understanding
text classification
named entity recognition
|
|
gptkbp:bfsParent
|
gptkb:XLM-R
|
|
gptkbp:bfsLayer
|
6
|