DNCON2

Training compute

9.5×10¹⁶ FLOP

Published

May 1, 2018

DNCON2 is an AI model developed by University of Missouri (United States), first published in May 2018. It works in the biology domain, on tasks such as proteins and protein folding prediction.

Training it took an estimated 9.5×10¹⁶ FLOP of compute (estimation method: hardware). It was trained on roughly 444M datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 173 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: University of Missouri
Country of organization: United States
Domain: Biology
Task: Proteins, Protein folding prediction
Training compute: 9.5×10¹⁶ FLOP
Compute estimation method: Hardware
Dataset size: 444M
Training time: 12 h
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 173
Epoch confidence: Likely