Hugging Face's logo

AnonHB
/
HarmAug_Guard_Model_deberta_v3_large_finetuned

Safetensors
deberta-v2
deberta-v3
Model card Files Community
AnonHB commited on
Commit
94a2604
•
1 Parent(s): 99498f5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@
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
 
 
6
 
7
 
8
 
9
+ Our model functions as a Guard Model, intended to classify the safety of conversations with LLMs and protect against LLM jailbreak attacks.
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