Update README.md
Browse files
README.md
CHANGED
|
@@ -5,14 +5,16 @@
|
|
| 5 |
# HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
|
| 6 |
|
| 7 |
|
| 8 |
-

|
| 9 |
-
|
| 10 |
-

|
| 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/)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
# HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
|
| 6 |
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
This model is a Guard Model, specifically designed to classify the safety of LLM conversations.
|
| 10 |
It is fine-tuned from DeBERTa-v3-large and trained using **HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models**.
|
| 11 |
The training process involves knowledge distillation paired with data augmentation, using our [**HarmAug Generated Dataset**](https://huggingface.co/datasets/AnonHB/HarmAug_generated_dataset).
|
| 12 |
|
| 13 |
|
| 14 |
+
For more information, please refer to our [anonymous github](https://anonymous.4open.science/r/HarmAug/)
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+

|
| 19 |
+
|
| 20 |
+

|