Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Salas, Pablo Gonzalez de Prado"'
Autor:
de la Rosa, Javier, Ponferrada, Eduardo G., Villegas, Paulo, Salas, Pablo Gonzalez de Prado, Romero, Manu, Grandury, Marıa
Publikováno v:
Procesamiento del Lenguaje Natural, 68 (2022): 13-23
The pre-training of large language models usually requires massive amounts of resources, both in terms of computation and data. Frequently used web sources such as Common Crawl might contain enough noise to make this pre-training sub-optimal. In this
Externí odkaz:
http://arxiv.org/abs/2207.06814
Autor:
de la Rosa, Javier, Ponferrada, Eduardo G., Villegas, Paulo, Salas, Pablo Gonzalez de Prado, Romero, Manu, Grandury, Marıa
Publikováno v:
RUA. Repositorio Institucional de la Universidad de Alicante
Universidad de Alicante (UA)
Universidad de Alicante (UA)
The pre-training of large language models usually requires massive amounts of resources, both in terms of computation and data. Frequently used web sources such as Common Crawl might contain enough noise to make this pre-training sub-optimal. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64231b118ed0c4cc1a30f4b67c6434a0
http://hdl.handle.net/10045/122846
http://hdl.handle.net/10045/122846