Search-Proven Best LSTM

Training compute

3.3×10¹⁵ FLOP

Parameters

20M

Published

Jul 6, 2015

Search-Proven Best LSTM is an AI model developed by Google (United States), first published in July 2015. It works in the language domain, on tasks such as language modeling and neural architecture search - nas.

Training it took an estimated 3.3×10¹⁵ FLOP of compute (estimation method: operation counting). The model has 20,000,000 parameters. It was trained on roughly 929K datapoints.

Access: Unreleased. Its weights are not openly released. The reference paper has 2,207 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google
Country of organization: United States
Domain: Language
Task: Language modeling, Neural Architecture Search - NAS
Training compute: 3.3×10¹⁵ FLOP
Compute estimation method: Operation counting
Parameters: 20,000,000
Dataset size: 929K
Model accessibility: Unreleased
Open weights: No
Citations: 2,207
Epoch confidence: Confident