AI models
ISS
Training compute
3.4×10¹⁵ FLOP
Parameters
11.1M
Published
Sep 15, 2017
ISS is an AI model developed by Duke University and Microsoft (United States), first published in September 2017. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 3.4×10¹⁵ FLOP of compute (estimation method: operation counting). The model has 11,100,000 parameters. It was trained on roughly 929K datapoints.
Access: Unreleased. Its weights are not openly released. The reference paper has 146 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Duke University, Microsoft
- Country of organization
- United States
- Domain
- Language
- Task
- Language modeling
- Training compute
- 3.4×10¹⁵ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 11,100,000
- Dataset size
- 929K
- Numerical format
- FP32
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 146
- 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