AI models
(ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)
Training compute
6.7×10¹⁷ FLOP
Parameters
185M
Published
Aug 30, 2018
(ensemble): AWD-LSTM-DOC (fin) × 5 (WT2) is an AI model developed by NTT Communication Science Laboratories and Tohoku University (Japan), first published in August 2018. It works in the language domain, on tasks such as language modeling.
Training it took an estimated 6.7×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 185,000,000 parameters. It was trained on roughly 2M datapoints.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 37 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- NTT Communication Science Laboratories, Tohoku University
- Country of organization
- Japan
- Domain
- Language
- Task
- Language modeling
- Training compute
- 6.7×10¹⁷ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 185,000,000
- Dataset size
- 2M
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 37
- Epoch confidence
- Confident
More from NTT Communication Science Laboratories,Tohoku University
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