🔥 cupidon-base-ro

Don’t be shy — cupidon-base-ro is here to charm your embeddings into alignment 💘. Based on the solid foundations of BlackKakapo/stsb-xlm-r-multilingual-ro and lovingly fine-tuned on Romanian STS data, this model brings more than just good looks to the table. Because in the end, true meaning isn’t just in the words... it's in how you embed them. 🧠💕

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:

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

model = SentenceTransformer('BlackKakapo/cupidon-base-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.

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-base-ro')
model = AutoModel.from_pretrained('BlackKakapo/cupidon-base-ro')

License

This dataset is licensed under Apache 2.0.

Citation

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

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