AI models
LSTM-3-layer+Gadam
Training compute
2.6×10¹⁶ FLOP
Parameters
24M
Published
Mar 2, 2020
LSTM-3-layer+Gadam is an AI model developed by University of Oxford, University of Bristol and University of Cambridge (United Kingdom), first published in March 2020. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 2.6×10¹⁶ FLOP of compute (estimation method: operation counting). The model has 24,000,000 parameters. It was trained on roughly 912.3K datapoints. Training ran on 1 NVIDIA GeForce RTX 2080 Ti 11GB.
Access: Unreleased. Its weights are not openly released. The reference paper has 5 citations. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- University of Oxford, University of Bristol, University of Cambridge
- Country of organization
- United Kingdom
- Domain
- Language
- Task
- Language modeling
- Training compute
- 2.6×10¹⁶ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 24,000,000
- Dataset size
- 912.3K
- Training hardware
- NVIDIA GeForce RTX 2080 Ti 11GB
- Chips used
- 1
- Training power draw
- 281 W
- Model accessibility
- Unreleased
- Open weights
- No
- Citations
- 5
- 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