RNN + char4-MS-vec

Parameters

226M

Published

Jul 17, 2019

RNN + char4-MS-vec is an AI model developed by NTT Communication Science Laboratories and Tohoku University (Japan), first published in July 2019. It works in the language domain, on tasks such as language modeling.

Epoch AI has no training-compute estimate for this model. The model has 226,000,000 parameters. Training ran on NVIDIA Tesla P100 PCIe 16GB.

Access: Unreleased. Its weights are not openly released. The reference paper has 26 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
Parameters: 226,000,000
Training hardware: NVIDIA Tesla P100 PCIe 16GB
Model accessibility: Unreleased
Open weights: No
Citations: 26
Epoch confidence: Confident

More from NTT Communication Science Laboratories,Tohoku University

(ensemble): AWD-LSTM-DOC (fin) × 5 (WT2)AWD-LSTM-DOC (fin) (23M)RNN + char3-MS-vec RNN + char2-MS-vec (ensemble): AWD-LSTM-DOC (fin) × 5 (PTB)AWD-LSTM-DOC (fin) (37M)

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