4 layer Densely Connected LSTM 14M (PTB)

Training compute

7.8×10¹⁵ FLOP

Parameters

14M

Published

Jul 19, 2017

4 layer Densely Connected LSTM 14M (PTB) is an AI model developed by Ghent University (Belgium), first published in July 2017. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 7.8×10¹⁵ FLOP of compute. The model has 14,000,000 parameters.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Ghent University
Country of organization: Belgium
Domain: Language
Task: Language modeling
Training compute: 7.8×10¹⁵ FLOP
Parameters: 14,000,000
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident