Logo
LLM Testframework
Short description
Evaluation of large language models
Source catalogue
0
1
0
0
Description
The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sustainability. While prior research has largely focused on energy consumption during model training, the inference phase has received comparatively less attention
This project evaluates the trade-offs between model accuracy and energy consumption in text classification inference.
Supported are traditional models, e.g. linear or xgboost, and large language models if available on https://huggingface.co/
Features
- Energy measurement
- Slurm scripts for HPC
Detailed information
Release date
Supported languages
English
Development status
Concept
License
MIT
Platforms
linux
Maintenance type
[internal] Internally maintained by the repository owner
Software type
standalone/backend
Technical Contacts
UBA KI-Lab