Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
+
|
5 |
+
# HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
|
6 |
+
|
7 |
+
|
8 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66f7bee63c7ffa79319b053b/bCNW62CvDpqbXUK4eZ4-b.png)
|
9 |
+
|
10 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66f7bee63c7ffa79319b053b/REbNDOhT31bv_XRa6-VzE.png)
|
11 |
+
|
12 |
+
|
13 |
+
This model is a Guard Model, specifically designed to classify the safety of LLM conversations.
|
14 |
+
It is fine-tuned from DeBERTa-v3-large and trained using **HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models**.
|
15 |
+
The training process involves knowledge distillation paired with data augmentation, using our [**HarmAug Generated Dataset**](https://huggingface.co/datasets/AnonHB/HarmAug_generated_dataset).
|
16 |
+
|
17 |
+
|
18 |
+
For more information, please refer to our [anonymous github](https://anonymous.4open.science/r/HarmAug/)
|