Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
Generated from Trainer
dataset_size:8066634
loss:MultipleNegativesRankingLoss
Instructions to use Parallia/Fairly-Multilingual-ModernBERT-Embed-BE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Parallia/Fairly-Multilingual-ModernBERT-Embed-BE with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Parallia/Fairly-Multilingual-ModernBERT-Embed-BE") sentences = [ "These three mysterious men came to our help.", "Three strange guys helped us then.", "These three black birds came in our garden.", "Some people are helpful.", "One, two, three... Who can guess the next digits?" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [5, 5] - Notebooks
- Google Colab
- Kaggle
How does it perform for unsupported language?
#4
by rjmehta - opened
If used on a Spanish language, will this work with average accuracy or would fail ?
Hi! It will be unlikely to work well on unsupported languages, as it was never trained for those languages.
I have plans to make more international versions of this model, with better training datasets and strategies, but I can't make any promise wrt the timeframe.
If you or anyone else want to support these efforts, I will remind that I'm accepting donations here to help me spend a larger propotion of my time on open research.