3 papers
cs.CL2024
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2
Pepijn de Reus, Ana Oprescu, Jelle Zuidema
This study examines quantisation and pruning strategies to reduce energy consumption in code Large Language Models (LLMs) inference. Using StarCoder2, we observe increased energy d…
cs.SE2024
Generating Energy-efficient code with LLMs
Tom Cappendijk, Pepijn de Reus, Ana Oprescu
The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to…
cs.LG2023
Energy cost and machine learning accuracy impact of k-anonymisation and synthetic data techniques
Pepijn de Reus, Ana Oprescu, Koen van Elsen
To address increasing societal concerns regarding privacy and climate, the EU adopted the General Data Protection Regulation (GDPR) and committed to the Green Deal. Considerable re…