Instructions to use SAVSNET/PetBERT-Tick-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SAVSNET/PetBERT-Tick-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SAVSNET/PetBERT-Tick-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SAVSNET/PetBERT-Tick-v2") model = AutoModelForSequenceClassification.from_pretrained("SAVSNET/PetBERT-Tick-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
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
- Downloads last month
- 25