Skip to main navigation Skip to search Skip to main content

IrEne-viz: Visualizing Energy Consumption of Transformer Models

  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

IrEne (Cao et al., 2021) is an energy prediction system that accurately predicts the interpretable inference energy consumption of a wide range of Transformer-based NLP models. We present the IrEne-viz tool, an online platform for visualizing and exploring energy consumption of various Transformer-based models easily. Additionally, we release a public API that can be used to access granular information about energy consumption of transformer models and their components. The live demo is available at http://stonybrooknlp.github.io/irene/demo/.

Original languageEnglish
Title of host publicationEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing
Subtitle of host publicationSystem Demonstrations
PublisherAssociation for Computational Linguistics (ACL)
Pages251-258
Number of pages8
ISBN (Electronic)9781955917117
DOIs
StatePublished - 2021
Event2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2021 - Virtual, Punta Cana, Dominican Republic
Duration: Nov 7 2021Nov 11 2021

Publication series

NameEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Conference

Conference2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2021
Country/TerritoryDominican Republic
CityVirtual, Punta Cana
Period11/7/2111/11/21

Fingerprint

Dive into the research topics of 'IrEne-viz: Visualizing Energy Consumption of Transformer Models'. Together they form a unique fingerprint.

Cite this