Update README.md
Browse files
README.md
CHANGED
|
@@ -21,9 +21,6 @@ base_model:
|
|
| 21 |
- openai-community/gpt2-medium
|
| 22 |
---
|
| 23 |
|
| 24 |
-
|
| 25 |
-
# Model Card
|
| 26 |
-
|
| 27 |
<p align="center">
|
| 28 |
<a href="https://arxiv.org/abs/2405.13967">
|
| 29 |
<img src="https://img.shields.io/badge/arXiv-2405.13967-B31B1B?logo=arxiv&logoColor=white" alt="arXiv">
|
|
@@ -36,6 +33,10 @@ base_model:
|
|
| 36 |
</a>
|
| 37 |
</p>
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
This model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
|
| 40 |
published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
|
| 41 |
|
|
|
|
| 21 |
- openai-community/gpt2-medium
|
| 22 |
---
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
<p align="center">
|
| 25 |
<a href="https://arxiv.org/abs/2405.13967">
|
| 26 |
<img src="https://img.shields.io/badge/arXiv-2405.13967-B31B1B?logo=arxiv&logoColor=white" alt="arXiv">
|
|
|
|
| 33 |
</a>
|
| 34 |
</p>
|
| 35 |
|
| 36 |
+
|
| 37 |
+
# ProFS Editing for Safety
|
| 38 |
+
|
| 39 |
+
|
| 40 |
This model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
|
| 41 |
published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
|
| 42 |
|