Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ Seanie Lee*, Haebin Seong*, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagn
|
|
| 17 |
|
| 18 |
Our model functions as a Guard Model, intended to classify the safety of conversations with LLMs and protect against LLM jailbreak attacks.
|
| 19 |
It is fine-tuned from DeBERTa-v3-large and trained using **HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models**.
|
| 20 |
-
The training process involves knowledge distillation paired with data augmentation, using our [**HarmAug Generated Dataset**].
|
| 21 |
|
| 22 |
|
| 23 |
For more information, please refer to our [github](https://github.com/imnotkind/HarmAug)
|
|
|
|
| 17 |
|
| 18 |
Our model functions as a Guard Model, intended to classify the safety of conversations with LLMs and protect against LLM jailbreak attacks.
|
| 19 |
It is fine-tuned from DeBERTa-v3-large and trained using **HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models**.
|
| 20 |
+
The training process involves knowledge distillation paired with data augmentation, using our [**HarmAug Generated Dataset**](https://drive.google.com/drive/folders/1oLUMPauXYtEBP7rvbULXL4hHp9Ck_yqg).
|
| 21 |
|
| 22 |
|
| 23 |
For more information, please refer to our [github](https://github.com/imnotkind/HarmAug)
|