Emojich -- zero-shot emoji generation using Russian language: a technical report

Shonenkov, Alex; Daria, Bakshandaeva,; Denis, Dimitrov,; Nikolich, Aleksandr

doi:10.48550/arxiv.2112.02448

Search citation statements

Order By: Relevance

Paper Sections

Select...

Methods1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

Publication Types

Select...

Other1

Relationship

Self Cite1

Independent0

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We present results for fine-tuning Malevich and Kandinsky on the Emojis dataset [26] and for training of Malevich with optimised variation of GELU [27] activation function. Training of the last mentioned version of Malevich allows us to consume about 10% less power and, consequently, produce less equivalent CO 2 emissions.…”

Section: Methodsmentioning

confidence: 99%

Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI

Budennyy¹,

Lazarev²,

Zakharenko³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The size and complexity of deep neural networks continue to grow exponentially, significantly increasing energy consumption for training and inference by these models. We introduce an opensource package eco2AI 1 to help data scientists and researchers to track energy consumption and equivalent CO 2 emissions of their models in a straightforward way. In eco2AI we put emphasis on accuracy of energy consumption tracking and correct regional CO 2 emissions accounting. We encourage research community to search for new optimal Artificial Intelligence (AI) architectures with a lower computational cost. The motivation also comes from the concept of AI-based green house gases sequestrating cycle with both Sustainable AI and Green AI pathways.

show abstract

Section: Methodsmentioning

confidence: 99%