AI models
IDPFold
Training compute
2.6×10²⁰ FLOP
Parameters
17.8M
Published
Sep 13, 2024
IDPFold is an AI model developed by Shandong University, BioMap Research, Fuzhou University and Shanghai Jiao Tong University (China), first published in September 2024. It works in the biology domain, on tasks such as protein folding prediction.
Training it took an estimated 2.6×10²⁰ FLOP of compute (estimation method: hardware). The model has 17,800,000 parameters. It was trained on roughly 30.9M datapoints. Training ran on NVIDIA A100.
It is built on top of ESM2-650M. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Shandong University, BioMap Research, Fuzhou University, Shanghai Jiao Tong University
- Country of organization
- China
- Domain
- Biology
- Task
- Protein folding prediction
- Training compute
- 2.6×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 17,800,000
- Dataset size
- 30.9M
- Training hardware
- NVIDIA A100
- Base model
- ESM2-650M
- 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