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/Barist.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KucLab/Barist.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="KucLab/Barist.2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("KucLab/Barist.2") model = AutoModelForSequenceClassification.from_pretrained("KucLab/Barist.2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download reports/adversarial.md from KucLab/Barist.2: direct link, hf CLI and curl.
- Browser
- Download file 374 Bytes
-
https://huggingface.co/KucLab/Barist.2/resolve/main/reports/adversarial.md
- Command line
-
hf download hf://KucLab/Barist.2/reports/adversarial.md
-
curl -L -o adversarial.md https://huggingface.co/KucLab/Barist.2/resolve/main/reports/adversarial.md
374 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 | 98.8% | 0.850 | | |
| | typo | 95.0% | 0.794 | | |
| | leet | 98.8% | 0.846 | | |
| | homoglyph | 99.4% | 0.882 | | |
| | zero_width | 100.0% | 0.886 | | |
| | case | 96.2% | 0.792 | | |