AI models
TransformerXL + spectrum control
Training compute
2.6×10¹⁹ FLOP
Parameters
151M
Published
Mar 11, 2020
TransformerXL + spectrum control is an AI model developed by University of California Los Angeles (UCLA) and JD.com (United States and China), first published in March 2020. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 2.6×10¹⁹ FLOP of compute (estimation method: operation counting,hardware). The model has 151,000,000 parameters. It was trained on roughly 103M datapoints. Training ran on 4 NVIDIA V100 for about 219 hours.
Access: Unreleased. Its weights are not openly released. The reference paper has 90 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- University of California Los Angeles (UCLA), JD.com
- Country of organization
- United States, China
- Domain
- Language
- Task
- Language modeling
- Training compute
- 2.6×10¹⁹ FLOP
- Compute estimation method
- Operation counting, Hardware
- Parameters
- 151,000,000
- Dataset size
- 103M
- Training hardware
- NVIDIA V100
- Chips used
- 4
- Training time
- 219 h
- Training power draw
- 2.5 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 90
- 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