AI models
Tensorized Transformer (257M)
Training compute
4.8×10¹⁸ FLOP
Parameters
257M
Published
Jun 24, 2019
Tensorized Transformer (257M) is an AI model developed by Tianjin University, Microsoft Research Asia and Beijing Institute of Technology (China), first published in June 2019. It works in the language domain, on tasks such as language modeling/generation.
Training it took an estimated 4.8×10¹⁸ FLOP of compute (estimation method: operation counting). The model has 257,000,000 parameters. It was trained on roughly 103M datapoints. Training ran on 2 NVIDIA P40.
Access: Unreleased. Its weights are not openly released. The reference paper has 194 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Tianjin University, Microsoft Research Asia, Beijing Institute of Technology
- Country of organization
- China
- Domain
- Language
- Task
- Language modeling/generation
- Training compute
- 4.8×10¹⁸ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 257,000,000
- Dataset size
- 103M
- Training hardware
- NVIDIA P40
- Chips used
- 2
- Training power draw
- 1.0 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 194
- Epoch confidence
- Confident
More from Tianjin University,Microsoft Research Asia,Beijing Institute of Technology
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