Using their new CEGI metric, the authors report that fine-tuned small models and low-bit quantization deliver near-large-model performance at a fraction of the carbon cost.
Towards the systematic reporting of the energy and carbon footprints of machine learning, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
CEGI: Measuring the trade-off between efficiency and carbon emissions for SLMs and VLMs
Using their new CEGI metric, the authors report that fine-tuned small models and low-bit quantization deliver near-large-model performance at a fraction of the carbon cost.