This is an ONNX-quantized version of the paraphrase-multilingual-MiniLM-L12-v2 model, optimized by Qdrant for fast inference. It generates high-quality sentence embeddings for 50+ languages and is primarily used for semantic similarity, retrieval-augmented generation, and vector search applications.
In the Embeddings & retrieval space, Paraphrase Multilingual MiniLM L12 V2 Onnx Q takes a focused approach. It focuses on enabling fast, multilingual semantic search and retrieval in vector databases with a lightweight embedding model. Paraphrase Multilingual MiniLM L12 V2 Onnx Q is an open-source project aimed at developers building RAG and semantic search systems. The project is open source (Apache-2.0). It ships for the web and API.
It is developed by Qdrant, and it first shipped in 2023. The project is developed in the open on GitHub with 3.1k stars and 4 commits in the last 90 days. Among its 4 catalogued features are multilingual, sentence similarity, and ONNX format.
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