AI models
Sandwich Transformer
Training compute
2.4×10¹⁹ FLOP
Parameters
209M
Published
Nov 10, 2019
Sandwich Transformer is an AI model developed by Allen Institute for AI and Facebook AI Research (United States and France), first published in November 2019. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 2.4×10¹⁹ FLOP of compute (estimation method: operation counting). The model has 209,000,000 parameters. It was trained on roughly 700M datapoints.
Access: Unreleased. Its weights are not openly released. The reference paper has 97 citations. Epoch AI rates the confidence of this record as speculative.
Full record
- Organization
- Allen Institute for AI, Facebook AI Research
- Country of organization
- United States, France
- Domain
- Language
- Task
- Language modeling
- Training compute
- 2.4×10¹⁹ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 209,000,000
- Dataset size
- 700M
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 97
- 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