AWD-LSTM-DRILL + dynamic evaluation† (WT2)

Training compute

4.1×10¹⁷ FLOP

Parameters

34M

Published

May 14, 2019

AWD-LSTM-DRILL + dynamic evaluation† (WT2) is an AI model developed by IDIAP (Switzerland), first published in May 2019. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 4.1×10¹⁷ FLOP of compute (estimation method: operation counting). The model has 34,000,000 parameters. It was trained on roughly 2M datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 7 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: IDIAP
Country of organization: Switzerland
Domain: Language
Task: Language modeling
Training compute: 4.1×10¹⁷ FLOP
Compute estimation method: Operation counting
Parameters: 34,000,000
Dataset size: 2M
Training time: 29 h
Numerical format: FP32
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 7
Epoch confidence: Likely