AI models
VDCNN (on Amazon Review Full dataset)
Training compute
5.7×10¹⁷ FLOP
Parameters
7.8M
Published
Jan 27, 2017
VDCNN (on Amazon Review Full dataset) is an AI model developed by Facebook AI Research and University of Le Mans (United States and France), first published in January 2017. It works in the language domain, on tasks such as text classification.
Training it took an estimated 5.7×10¹⁷ FLOP of compute (estimation method: hardware). The model has 7,800,000 parameters. Training ran on 1 NVIDIA Tesla K40s.
Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Facebook AI Research, University of Le Mans
- Country of organization
- United States, France
- Domain
- Language
- Task
- Text classification
- Training compute
- 5.7×10¹⁷ FLOP
- Compute estimation method
- Hardware
- Parameters
- 7,800,000
- Training hardware
- NVIDIA Tesla K40s
- Chips used
- 1
- Training power draw
- 282 W
- 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