{"@context":"https://schema.org","@type":"Dataset","license":"https://creativecommons.org/licenses/by/4.0/","creditText":"Data: AintOnlyAI (https://aintonlyai.world), CC-BY-4.0","identifier":"the-pile","name":"The Pile","description":"Open large-scale pretraining dataset behind a generation of open language models.","url":"https://pile.eleuther.ai","sameAs":"https://pile.eleuther.ai","additionalType":"dataset","keywords":"data, research","additionalProperty":{"@type":"PropertyValue","name":"ai_adjacency_score","value":64}}