Model Card Added
Browse files
README.md
CHANGED
|
@@ -1,3 +1,66 @@
|
|
| 1 |
---
|
| 2 |
license: llama2
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: llama2
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
---
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
|
| 12 |
+
### Model Description
|
| 13 |
+
|
| 14 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
- **Developed by:** Tomasz Limisiewicz, David Mareček, Tomáš Musil
|
| 19 |
+
- **Language(s) (NLP):** English
|
| 20 |
+
- **Adapted from model:** LLaMA 13B
|
| 21 |
+
|
| 22 |
+
### Model Sources
|
| 23 |
+
|
| 24 |
+
<!-- Provide the basic links for the model. -->
|
| 25 |
+
|
| 26 |
+
- **Repository:** [Link](github.com/tomlimi/DAMA)
|
| 27 |
+
- **Paper:** [Link](openreview.net/pdf?id=XIZEFyVGC9)
|
| 28 |
+
|
| 29 |
+
## Uses
|
| 30 |
+
|
| 31 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 32 |
+
|
| 33 |
+
### Direct Use
|
| 34 |
+
|
| 35 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 36 |
+
|
| 37 |
+
The model is the adapted version of LLaMA 13B for decreasing gender bias.
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Bias, Risks, and Limitations
|
| 41 |
+
|
| 42 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 43 |
+
|
| 44 |
+
The model mitigates the gender bias of the original model.
|
| 45 |
+
Thus, it is better suited for the generation and processing of texts in sensitive domains.
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
## Citation
|
| 50 |
+
|
| 51 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 52 |
+
|
| 53 |
+
**BibTeX:**
|
| 54 |
+
|
| 55 |
+
```
|
| 56 |
+
@inproceedings{
|
| 57 |
+
limisiewicz2024debiasing,
|
| 58 |
+
title={Debiasing Algorithm through Model Adaptation},
|
| 59 |
+
author={Tomasz Limisiewicz and David Mare{\v{c}}ek and Tom{\'a}{\v{s}} Musil},
|
| 60 |
+
booktitle={The Twelfth International Conference on Learning Representations},
|
| 61 |
+
year={2024},
|
| 62 |
+
url={https://openreview.net/forum?id=XIZEFyVGC9}
|
| 63 |
+
}
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
|