BIG-G 137B

Training compute

5.6×10²³ FLOP

Parameters

137B

Published

Jun 9, 2022

BIG-G 137B is an AI model developed by Google (United States), first published in June 2022. It works in the language domain, on tasks such as language modeling/generation.

Training it took an estimated 5.6×10²³ FLOP of compute (estimation method: operation counting). The model has 137,000,000,000 parameters. It was trained on roughly 681.2B datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 2,441 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google
Country of organization: United States
Domain: Language
Task: Language modeling/generation
Training compute: 5.6×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 137,000,000,000
Dataset size: 681.2B
Model accessibility: Unreleased
Open weights: No
Citations: 2,441
Epoch confidence: Confident