DiffQ Transformer (16L)

Training compute

3×10¹⁹ FLOP

Parameters

247M

Published

Apr 20, 2021

DiffQ Transformer (16L) is an AI model developed by Meta AI (United States), first published in April 2021. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 3×10¹⁹ FLOP of compute (estimation method: operation counting). The model has 247,000,000 parameters. It was trained on roughly 103M datapoints. Training ran on NVIDIA V100.

Access: Unreleased. Its weights are not openly released. The reference paper has 63 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 3×10¹⁹ FLOP
Compute estimation method: Operation counting
Parameters: 247,000,000
Dataset size: 103M
Training hardware: NVIDIA V100
Model accessibility: Unreleased
Open weights: No
Citations: 63
Epoch confidence: Confident