CrossEncoder for Slovene NLI
The model was trained using the SentenceTransformers CrossEncoder class.
It is based on SloBerta, a monolingual Slovene model.
Training
This model was trained on the SI-NLI dataset.
More details and the training script are available here: repo
Performance
The model achieves the following metrics:
- Test accuracy: 75.95
- Dev accuracy: 75.14
Usage
The model can be used for inference using the below code:
from sentence_transformers import CrossEncoder
model = CrossEncoder('jacinthes/cross-encoder-sloberta-si-nli')
premise = 'Pojdi z menoj v toplice.'
hypothesis = 'Bova lepa bova fit.'
prediction = model.predict([premise, hypothesis])
int2label = {0: 'entailment', 1: 'neutral', 2:'contradiction'}
print(int2label[prediction.argmax()])
- Downloads last month
- 4