Login / Signup

Language models scale reliably with over-training and on downstream tasks.

Samir Yitzhak GadreGeorgios SmyrnisVaishaal ShankarSuchin GururanganMitchell WortsmanRulin ShaoJean MercatAlex FangJeffrey LiSedrick KehRui XinMarianna NezhurinaIgor VasiljevicJenia JitsevAlexandros G. DimakisGabriel IlharcoShuran SongThomas KollarYair CarmonAchal DaveReinhard HeckelNiklas MuennighoffLudwig Schmidt
Published in: CoRR (2024)
Keyphrases