shawhin/bert-phishing-classifier_student_4bit

bert-phishing-classifier_student

This model is a quantized version of shawhin/bert-phishing-classifier_student trained via knowledge distillation from shawhin/bert-phishing-classifier_teacher using the shawhin/phishing-site-classification dataset. It achieves the following results on the validation set:

• Accuracy: 0.9356
• Precision: 0.9757
• Recall: 0.8933
• F1 Score: 0.9327

Model description

Quantized student model for model compression example.

Video | Blog | Example code

Intended uses & limitations

This model was created for educational purposes.

Training and evaluation data

The Training, Testing, and Validation data are available here: shawhin/phishing-site-classification.