Edit model card

Fine-tuned model that detects profanity in text.

This is the "tiny" version, see https://huggingface.co/tarekziade/pardonmyai

Evaluation:

  • Accuracy: 0.9633
  • Precision: 0.9378
  • Recall: 0.8746
  • F1 Score: 0.9051
  • AUC-ROC: 0.9892
Downloads last month
8
Safetensors
Model size
14.4M params
Tensor type
F32
·

Finetuned from

Dataset used to train tarekziade/pardonmyai-tiny

Collection including tarekziade/pardonmyai-tiny