Text Classification
Transformers
Safetensors
Moroccan Arabic
Arabic
bert
toxicity-detection
content-moderation
offensive-language
moroccan-darija
darija
low-resource-languages
Eval Results (legacy)
text-embeddings-inference
Instructions to use TypicaAI/DarijaToxicityDetector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TypicaAI/DarijaToxicityDetector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="TypicaAI/DarijaToxicityDetector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("TypicaAI/DarijaToxicityDetector") model = AutoModelForSequenceClassification.from_pretrained("TypicaAI/DarijaToxicityDetector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update model card: add July 2026 benchmark re-run (claude-haiku-4-5, omni-moderation, mistral-moderation)
Verified signature111d19a -
Add model card (dataset docs, benchmark, citation arXiv:2505.04640)
Verified signature6b60d91 -
Add tokenizer
Verified signature9b6d56a -
Add DarijaBERT binary toxicity model (best checkpoint, acc 0.8307)
Verified signature96dcfab -
initial commit
Verified signature139e65d