AI models
DistilProtBert
Training compute
1.9×10²⁰ FLOP
Parameters
230M
Published
Sep 18, 2022
DistilProtBert is an AI model developed by Bar-Ilan University (Israel), first published in September 2022. It works in the biology domain, on tasks such as proteins and protein folding prediction.
Training it took an estimated 1.9×10²⁰ FLOP of compute (estimation method: hardware). The model has 230,000,000 parameters. It was trained on roughly 11B datapoints. Training ran on NVIDIA Tesla V100 DGXS 32 GB for about 288 hours.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 39 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Bar-Ilan University
- Country of organization
- Israel
- Domain
- Biology
- Task
- Proteins, Protein folding prediction
- Training compute
- 1.9×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 230,000,000
- Dataset size
- 11B
- Training hardware
- NVIDIA Tesla V100 DGXS 32 GB
- Training time
- 288 h
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 39
- Epoch confidence
- Confident
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