AWD-LSTM-MoS+PDR + dynamic evaluation (PTB)

Training compute

4.1×10¹⁷ FLOP

Parameters

60.9M

Published

Aug 14, 2018

AWD-LSTM-MoS+PDR + dynamic evaluation (PTB) is an AI model developed by IBM (United States), first published in August 2018. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 4.1×10¹⁷ FLOP of compute. The model has 60,852,800 parameters. It was trained on roughly 929K datapoints.

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

Full record

Organization: IBM
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 4.1×10¹⁷ FLOP
Parameters: 60,852,800
Dataset size: 929K
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Likely