Luminous-supreme

Training compute

3.5×10²³ FLOP

Parameters

70B

Published

Aug 15, 2022

Luminous-supreme is an AI model developed by Aleph Alpha (Germany), first published in August 2022. It works in the language domain, on tasks such as language generation.

Training it took an estimated 3.5×10²³ FLOP of compute (estimation method: hardware,operation counting). The model has 70,000,000,000 parameters. It was trained on roughly 1.1T datapoints. Training ran on 512 NVIDIA A100 SXM4 40 GB,NVIDIA A100 SXM4 80 GB for about 2K hours.

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

Full record

Organization: Aleph Alpha
Country of organization: Germany
Domain: Language
Task: Language generation
Training compute: 3.5×10²³ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 70,000,000,000
Dataset size: 1.1T
Training hardware: NVIDIA A100 SXM4 40 GB, NVIDIA A100 SXM4 80 GB
Chips used: 512
Training time: 2,016 h
Model accessibility: API access
Open weights: No
Epoch confidence: Confident