PLUG

Training compute

3.6×10²² FLOP

Parameters

27B

Published

Apr 19, 2021

PLUG is an AI model developed by Alibaba (China), first published in April 2021. It works in the language domain, on tasks such as language modeling/generation.

Training it took an estimated 3.6×10²² FLOP of compute (estimation method: hardware). The model has 27,000,000,000 parameters. It was trained on roughly 60B datapoints. Training ran on 128 NVIDIA A100 for about 840 hours. The compute alone is estimated at $109K in 2023 dollars.

Access: Hosted access (no API). Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Alibaba
Country of organization: China
Domain: Language
Task: Language modeling/generation
Training compute: 3.6×10²² FLOP
Compute estimation method: Hardware
Parameters: 27,000,000,000
Dataset size: 60B
Training hardware: NVIDIA A100
Chips used: 128
Training time: 840 h
Training power draw: 103.7 kW
Training cost (2023 USD): $109K
Model accessibility: Hosted access (no API)
Open weights: No
Epoch confidence: Confident