DeBERTaV3large

Training compute

1.1×10²⁰ FLOP

Parameters

418M

Published

Nov 18, 2021

DeBERTaV3large is an AI model developed by Microsoft Research (United States), first published in November 2021. It works in the language domain, on tasks such as question answering and language modeling/generation.

Training it took an estimated 1.1×10²⁰ FLOP of compute (estimation method: operation counting). The model has 418,000,000 parameters. It was trained on roughly 42.7B datapoints.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Microsoft Research
Country of organization: United States
Domain: Language
Task: Question answering, Language modeling/generation
Training compute: 1.1×10²⁰ FLOP
Compute estimation method: Operation counting
Parameters: 418,000,000
Dataset size: 42.7B
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Likely