AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2)

Training compute

3×10¹⁷ FLOP

Parameters

33M

Published

Aug 7, 2017

AWD-LSTM - 3-layer LSTM (tied) + continuous cache pointer (WT2) is an AI model developed by Salesforce Research (United States), first published in August 2017. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 3×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 33,000,000 parameters. It was trained on roughly 2M datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 1,176 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Salesforce Research
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 3×10¹⁷ FLOP
Compute estimation method: Operation counting
Parameters: 33,000,000
Dataset size: 2M
Model accessibility: Unreleased
Open weights: No
Citations: 1,176
Epoch confidence: Confident