Downloads · 30 days
91
0% of all-time downloads
distilbert-base-uncased-detected-jailbreak
Necent/distilbert-base-uncased-detected-jailbreak
distilbert-base-uncased-detected-jailbreak is a text classification model from Necent. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
Модель на основе DistilBERT для обнаружения попыток обхода фильтров (jailbreak) в текстах.
All-time downloads
4.4M
Public
Parameters
67M
804 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt536 MB · 67%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 17, 2024
- Updated
- May 29, 2025
- SHA
- cfd6726c
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
🧠 DistilBERT for Jailbreak Detection
Модель на основе DistilBERT для обнаружения попыток обхода фильтров (jailbreak) в текстах.
📚 Детали модели
- Архитектура: DistilBERT
- Задача: Классификация текста (обнаружение jailbreak)
- Входные данные: Текстовые строки
- Выходные данные: Метка класса (например,
jailbreakилиsafe)
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Apr 17, 2024
- Updated
- May 29, 2025