# 768-dimensional embeddings

This is a Portuguese sentence encoder based on sentence-transformers, which maps text to a 768-dimensional vector space, suitable for tasks such as semantic search and text clustering.

A long-context bi-encoder based on MosaicML's pre-trained BERT with 1024 sequence length, for sentence and paragraph embeddings

This is a sentence-transformers based model that can map sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks like sentence similarity computation and semantic search.

BERT-based Dutch sentence transformation model, designed for sentence similarity tasks