AI models
Fold2Seq
Training compute
1.4×10¹⁷ FLOP
Parameters
12.4M
Published
Jun 24, 2021
Fold2Seq is an AI model developed by IBM and Texas A&M (United States), first published in June 2021. It works in the biology domain, on tasks such as proteins, protein generation, protein inverse folding and protein fold classification.
Training it took an estimated 1.4×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 12,427,904 parameters. It was trained on roughly 46K datapoints. Training ran on 2 NVIDIA Tesla K80.
Access: Unreleased. Its weights are not openly released. The reference paper has 56 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- IBM, Texas A&M
- Country of organization
- United States
- Domain
- Biology
- Task
- Proteins, Protein generation, Protein inverse folding, Protein fold classification
- Training compute
- 1.4×10¹⁷ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 12,427,904
- Dataset size
- 46K
- Training hardware
- NVIDIA Tesla K80
- Chips used
- 2
- Training power draw
- 1.2 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 56
- Epoch confidence
- Speculative
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