rTop-k(distributed setting)

Training compute

1.4×10¹⁶ FLOP

Parameters

69M

Published

May 21, 2020

rTop-k(distributed setting) is an AI model developed by Stanford University (United States), first published in May 2020. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 1.4×10¹⁶ FLOP of compute (estimation method: operation counting). The model has 69,000,000 parameters. It was trained on roughly 912.3K datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 71 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Stanford University
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 1.4×10¹⁶ FLOP
Compute estimation method: Operation counting
Parameters: 69,000,000
Dataset size: 912.3K
Model accessibility: Unreleased
Open weights: No
Citations: 71
Epoch confidence: Likely