| --- |
| library_name: transformers |
| language: |
| - en |
| base_model: |
| - SAVSNET/PetBERT |
| --- |
| |
| # Model Card for Model ID |
|
|
| PetBERT-Tick-v2 is a BERT-based binary classifier, fine-tuned to detect the presence ot ticks in veterinary electronic health records. It used PetBERT as it's base model, a model domain adapted from BERT-base using 5.1 millon veterinary electronic health records from dogs and cats. |
|
|
| ## Labels |
| - `tick_absent` (0) |
| - `tick_present` (1) |
|
|
| **Model Performance** |
|
|
| | |precision |recall |f1-score |support | |
| |------------|------------------|------------------|------------------|------------------| |
| |0 |0.977|0.987|0.982|12001 | |
| |1 |0.957|0.927 |0.942 |3841 | |
| |accuracy | | |0.972 |15842 | |
| |macro avg |0.967|0.957|0.962|15842 | |
| |weighted avg|0.972|0.972|0.972|15842 | |
|
|
| Classification Threshold = 0.943 |
|
|
|
|
