ProtBFN

Training compute

3.9×10²² FLOP

Parameters

650M

Published

Sep 24, 2024

ProtBFN is an AI model developed by InstaDeep (United Kingdom), first published in September 2024. It works in the biology domain, on tasks such as protein or nucleotide language model (plm/nlm).

Training it took an estimated 3.9×10²² FLOP of compute (estimation method: hardware). The model has 650,000,000 parameters. Training ran on 256 Google TPU v4 for about 432 hours.

The reference paper has 16 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: InstaDeep
Country of organization: United Kingdom
Domain: Biology
Task: Protein or nucleotide language model (pLM/nLM)
Training compute: 3.9×10²² FLOP
Compute estimation method: Hardware
Parameters: 650,000,000
Training hardware: Google TPU v4
Chips used: 256
Training time: 432 h
Training power draw: 171.4 kW
Citations: 16
Epoch confidence: Confident