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
18
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train jacinthes/cross-encoder-sloberta-si-nli