AI models
SPN-4+KN5
Training compute
4.4×10¹⁶ FLOP
Parameters
5M
Published
Sep 14, 2014
SPN-4+KN5 is an AI model developed by Singapore University of Technology & Design and DSO National Laboratories (Singapore), first published in September 2014. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 4.4×10¹⁶ FLOP of compute (estimation method: hardware). The model has 5,000,000 parameters. It was trained on roughly 929K datapoints. Training ran on 1 NVIDIA Tesla C2075 for about 40 hours.
Access: Unreleased. Its weights are not openly released. The reference paper has 102 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Singapore University of Technology & Design, DSO National Laboratories
- Country of organization
- Singapore
- Domain
- Language
- Task
- Language modeling
- Training compute
- 4.4×10¹⁶ FLOP
- Compute estimation method
- Hardware
- Parameters
- 5,000,000
- Dataset size
- 929K
- Training hardware
- NVIDIA Tesla C2075
- Chips used
- 1
- Training time
- 40 h
- Training power draw
- 290 W
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 102
- Epoch confidence
- Likely
More from Singapore University of Technology & Design,DSO National Laboratories
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