Linear Transformer (small)

Training compute

1.7×10¹⁸ FLOP

Parameters

40M

Published

Feb 22, 2021

Linear Transformer (small) is an AI model developed by IDSIA and SUPSI (Switzerland), first published in February 2021. It works in the language domain, on tasks such as language modeling and translation.

Training it took an estimated 1.7×10¹⁸ FLOP of compute (estimation method: operation counting). The model has 40,000,000 parameters. It was trained on roughly 103M datapoints. Training ran on 2 NVIDIA V100.

Access: Unreleased. Its weights are not openly released. The reference paper has 405 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: IDSIA, SUPSI
Country of organization: Switzerland
Domain: Language
Task: Language modeling, Translation
Training compute: 1.7×10¹⁸ FLOP
Compute estimation method: Operation counting
Parameters: 40,000,000
Dataset size: 103M
Training hardware: NVIDIA V100
Chips used: 2
Training power draw: 1.2 kW
Model accessibility: Unreleased
Open weights: No
Citations: 405
Epoch confidence: Confident