Say hello to cupidon-mini-ro — the bigger sibling of tiny, but still on the lightweight side at just ~90MB. Fine-tuned from sentence-transformers/all-MiniLM-L6-v2, this sentence-transformers model smoothly maps Romanian sentences into sleek dense vectors for tasks like semantic search, clustering, and textual similarity. It’s living proof that sometimes, a little more size is just right — still fast, still efficient, and definitely charming enough to handle your STS needs without hogging your hardware. 😎💡

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

python

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('BlackKakapo/cupidon-mini-ro')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

python

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BlackKakapo/cupidon-mini-ro')
model = AutoModel.from_pretrained('BlackKakapo/cupidon-mini-ro')

License

This dataset is licensed under Apache 2.0.

Citation

If you use BlackKakapo/cupidon-mini-ro in your research, please cite this model as follows:

@misc{cupidon-mini-ro,
  title={BlackKakapo/cupidon-mini-ro},
  author={BlackKakapo},
  year={2025},
}