|
gptkbp:instanceOf
|
large language model
|
|
gptkbp:announced
|
2022-04-04
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:author
|
gptkb:Jacob_Devlin
gptkb:Aakanksha_Chowdhery
gptkb:Gaurav_Mishra
gptkb:Maarten_Bosma
gptkb:Sharan_Narang
|
|
gptkbp:basedOn
|
gptkb:Pathways_system
|
|
gptkbp:citation
|
1000+
|
|
gptkbp:developedBy
|
gptkb:Google
|
|
gptkbp:fullName
|
gptkb:Pathways_Language_Model
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Google PaLM
|
|
gptkbp:mobileAppAvailable
|
yes
|
|
gptkbp:notable_for
|
gptkb:public_speaker
creative writing
translator
code generation
summarization
commonsense reasoning
code completion
code debugging
code explanation
explanations
multi-step reasoning
math reasoning
|
|
gptkbp:notableFeature
|
scalable architecture
few-shot learning
chain-of-thought reasoning
|
|
gptkbp:notablePublication
|
gptkb:PaLM:_Scaling_Language_Modeling_with_Pathways
|
|
gptkbp:openSource
|
no
|
|
gptkbp:paperPublishedOn
|
2022
|
|
gptkbp:parameter
|
540 billion
|
|
gptkbp:predecessor
|
gptkb:BERT
|
|
gptkbp:relatedTo
|
gptkb:Gemini
gptkb:Google_Bard
|
|
gptkbp:successor
|
gptkb:PaLM_2
|
|
gptkbp:supports
|
English
multiple languages
|
|
gptkbp:trainer
|
multilingual datasets
|
|
gptkbp:trainingDataSize
|
780 billion tokens
|
|
gptkbp:usedFor
|
natural language processing
translator
question answering
summarization
text generation
reasoning tasks
|
|
gptkbp:usedIn
|
gptkb:Google_Workspace
gptkb:Google_Cloud_AI_products
|
|
gptkbp:bfsParent
|
gptkb:Claude_2
|
|
gptkbp:bfsLayer
|
6
|