Text Classification
Transformers
ONNX
Safetensors
llama
safety
content-moderation
multi-label
multilingual
tiny-language-model
from-scratch
distilled
text-embeddings-inference
Instructions to use KucLab/Censer.8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.8") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download reports/adversarial.md from KucLab/Censer.8: direct link, hf CLI and curl.
- Browser
- Download file 376 Bytes
-
https://huggingface.co/KucLab/Censer.8/resolve/main/reports/adversarial.md
- Command line
-
hf download hf://KucLab/Censer.8/reports/adversarial.md
-
curl -L -o adversarial.md https://huggingface.co/KucLab/Censer.8/resolve/main/reports/adversarial.md
376 Bytes
| # Adversarial robustness (unsafe items under text attacks) | |
| n=160 unsafe items, threshold 0.5, detection rate = fraction still flagged unsafe. | |
| | Attack | Detection rate | Mean unsafe prob | | |
| | --- | --- | --- | | |
| | clean | 100.0% | 0.890 | | |
| | typo | 92.5% | 0.826 | | |
| | leet | 96.9% | 0.869 | | |
| | homoglyph | 100.0% | 0.922 | | |
| | zero_width | 100.0% | 0.914 | | |
| | case | 96.2% | 0.817 | | |