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.9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Censer.9 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Censer.9")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Censer.9") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Censer.9", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download reports/adversarial.json from KucLab/Censer.9: direct link, hf CLI and curl.
- Browser
- Download file 721 Bytes
-
https://huggingface.co/KucLab/Censer.9/resolve/main/reports/adversarial.json
- Command line
-
hf download hf://KucLab/Censer.9/reports/adversarial.json
-
curl -L -o adversarial.json https://huggingface.co/KucLab/Censer.9/resolve/main/reports/adversarial.json
721 Bytes
| { | |
| "checkpoint": "checkpoints9h/best.pt", | |
| "n_items": 160, | |
| "attacks": { | |
| "clean": { | |
| "n": 160, | |
| "detection_rate@0.5": 0.9938, | |
| "mean_unsafe_prob": 0.9166 | |
| }, | |
| "typo": { | |
| "n": 160, | |
| "detection_rate@0.5": 0.9437, | |
| "mean_unsafe_prob": 0.8584 | |
| }, | |
| "leet": { | |
| "n": 160, | |
| "detection_rate@0.5": 0.975, | |
| "mean_unsafe_prob": 0.9065 | |
| }, | |
| "homoglyph": { | |
| "n": 160, | |
| "detection_rate@0.5": 1.0, | |
| "mean_unsafe_prob": 0.9468 | |
| }, | |
| "zero_width": { | |
| "n": 160, | |
| "detection_rate@0.5": 1.0, | |
| "mean_unsafe_prob": 0.9394 | |
| }, | |
| "case": { | |
| "n": 160, | |
| "detection_rate@0.5": 0.9563, | |
| "mean_unsafe_prob": 0.8334 | |
| } | |
| } | |
| } |