metadata
license: llama2
language:
- en
DAMA 33B
Model Details
Model Description
- Developed by: Tomasz Limisiewicz, David Mareček, Tomáš Musil
- Language(s) (NLP): English
- Adapted from model: LLaMA 33B
Model Sources
Uses
Direct Use
The model is the adapted version of LLaMA 33B for decreasing gender bias.
Bias, Risks, and Limitations
The model mitigates the gender bias of the original model. Thus, it is better suited for the generation and processing of texts in sensitive domains.
Citation
BibTeX:
@inproceedings{
limisiewicz2024debiasing,
title={Debiasing Algorithm through Model Adaptation},
author={Tomasz Limisiewicz and David Mare{\v{c}}ek and Tom{\'a}{\v{s}} Musil},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=XIZEFyVGC9}
}