Zoneout + Variational LSTM (PTB)

Training compute

7.1×10¹⁵ FLOP

Parameters

20M

Published

Sep 26, 2016

Zoneout + Variational LSTM (PTB) is an AI model developed by MetaMind Inc (United States), first published in September 2016. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 7.1×10¹⁵ FLOP of compute. The model has 20,000,000 parameters.

Access: Unreleased. Its weights are not openly released. The reference paper has 4,010 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: MetaMind Inc
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 7.1×10¹⁵ FLOP
Parameters: 20,000,000
Model accessibility: Unreleased
Open weights: No
Citations: 4,010
Epoch confidence: Confident