AI models
ELECTRA
Training compute
3.1×10²¹ FLOP
Parameters
335M
Published
Mar 23, 2020
ELECTRA is an AI model developed by Stanford University, Google and Google Brain (United States), first published in March 2020. It works in the language domain, on tasks such as text autocompletion.
Training it took an estimated 3.1×10²¹ FLOP of compute (estimation method: reported). The model has 335,000,000 parameters. It was trained on roughly 33B datapoints.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 2,968 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Stanford University, Google, Google Brain
- Country of organization
- United States
- Domain
- Language
- Task
- Text autocompletion
- Training compute
- 3.1×10²¹ FLOP
- Compute estimation method
- Reported
- Parameters
- 335,000,000
- Dataset size
- 33B
- Numerical format
- FP32
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 2,968
- Epoch confidence
- Likely
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