AI models
UDSMProt
Training compute
6.4×10¹⁷ FLOP
Parameters
28.3M
Published
Sep 4, 2019
UDSMProt is an AI model developed by Fraunhofer Heinrich Hertz Institute (Germany), first published in September 2019. It works in the biology domain, on tasks such as proteins, protein or nucleotide language model (plm/nlm) and enzyme function prediction.
Training it took an estimated 6.4×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 28,303,800 parameters. It was trained on roughly 149.7M datapoints.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Fraunhofer Heinrich Hertz Institute
- Country of organization
- Germany
- Domain
- Biology
- Task
- Proteins, Protein or nucleotide language model (pLM/nLM), Enzyme function prediction
- Training compute
- 6.4×10¹⁷ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 28,303,800
- Dataset size
- 149.7M
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Likely
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models