clip-ViT-B-32-multilingual-v1 is an open-source multilingual variant of the CLIP ViT-B/32 model hosted on Hugging Face. It produces high-quality embeddings for text in multiple languages and supports cross-modal text-image similarity. The model is integrated with the sentence-transformers library, making it easy to use for semantic search, clustering, and retrieval-augmented generation applications across languages.
In the Foundation models & chat space, Clip ViT B 32 Multilingual takes a focused approach. It focuses on generating high-quality multilingual text and image embeddings for semantic similarity and retrieval tasks. Clip ViT B 32 Multilingual is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Behind Clip ViT B 32 Multilingual is Sentence Transformers, and it first shipped in 2019. The project is developed in the open on GitHub with 19k stars and 92 commits in the last 90 days. Among its 3 catalogued features are multilingual embeddings, sentence similarity, and text-to-image alignment.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do