AFP+FPI (WT2)

Training compute

6.5×10¹⁵ FLOP

Parameters

13.6M

Published

Jun 4, 2021

AFP+FPI (WT2) is an AI model developed by University of Sheffield (United Kingdom), first published in June 2021. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 6.5×10¹⁵ FLOP of compute. The model has 13,600,000 parameters.

Access: Unreleased. Its weights are not openly released. The reference paper has 4 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: University of Sheffield
Country of organization: United Kingdom
Domain: Language
Task: Language modeling
Training compute: 6.5×10¹⁵ FLOP
Parameters: 13,600,000
Model accessibility: Unreleased
Open weights: No
Citations: 4
Epoch confidence: Confident