Sentence Embedding LaBSE

🚀 LaBSE

This is a PyTorch port of the LaBSE model, which can map 109 languages to a shared vector space.

🚀 Quick Start

This is a port of the LaBSE model to PyTorch. It can be used to map 109 languages to a shared vector space.

✨ Features

• Supports multilingual processing, including languages like Afrikaans (af), Albanian (sq), Amharic (am), etc.
• Can be used for sentence similarity tasks and feature extraction.

📦 Installation

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

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

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

model = SentenceTransformer('sentence-transformers/LaBSE')
embeddings = model.encode(sentences)
print(embeddings)

📚 Documentation

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

🔧 Technical Details

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): Normalize()
)

📄 License

This project is licensed under the apache-2.0 license.

Citing & Authors

Have a look at LaBSE for the respective publication that describes LaBSE.