MoE-1.1T

Training compute

2.2×10²² FLOP

Parameters

1.1T

Published

Dec 20, 2021

MoE-1.1T is an AI model developed by Meta AI (United States), first published in December 2021. It works in the language domain, on tasks such as language modeling/generation and question answering.

Training it took an estimated 2.2×10²² FLOP of compute (estimation method: reported). The model has 1,100,000,000,000 parameters. It was trained on roughly 112B datapoints. Training ran on NVIDIA A100.

Access: Open weights (non-commercial). Its weights are openly available. The reference paper has 241 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/generation, Question answering
Training compute: 2.2×10²² FLOP
Compute estimation method: Reported
Parameters: 1,100,000,000,000
Dataset size: 112B
Training hardware: NVIDIA A100
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Citations: 241
Epoch confidence: Confident