This is a multilingual version of the MPNet sentence embedding model, converted for use with Transformers.js to run directly in web browsers. It generates high-quality embeddings for semantic similarity, paraphrase detection, and clustering across many languages. The model is particularly useful for web-based semantic search and recommendation applications.
In the Foundation models & chat space, Paraphrase Multilingual Mpnet Base takes a focused approach. It focuses on creating high-quality multilingual text embeddings that run efficiently in web browsers using ONNX or Transformers.js. Paraphrase Multilingual Mpnet Base is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web and the command line.
It is developed by Xenova, and the product first shipped in 2023. Among its 3 catalogued features are Sentence Embeddings, multilingual, and Paraphrase Detection.
Latest indexed changes and source events
Xenova/paraphrase-multilingual-mpnet-base-v2 verified by the PulseGate indexer
Other apps tracked under the same category.
