Griffin

Training compute

1.6×10²² FLOP

Parameters

14B

Published

Feb 29, 2024

Griffin is an AI model developed by Google DeepMind (United States), first published in February 2024. It works in the language domain, on tasks such as language modeling/generation and chat.

Training it took an estimated 1.6×10²² FLOP of compute (estimation method: reported). The model has 14,000,000,000 parameters. It was trained on roughly 300B datapoints. Training ran on Google TPU v3.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Chat
Training compute: 1.6×10²² FLOP
Compute estimation method: Reported
Parameters: 14,000,000,000
Dataset size: 300B
Training hardware: Google TPU v3
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident