{"repo":"yuniko-software/bge-m3-onnx","free":true,"listed":false,"github":"https://github.com/yuniko-software/bge-m3-onnx","clone":"git clone https://github.com/yuniko-software/bge-m3-onnx.git","description":"ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#, Java, and Python implementations. Generates all three embedding types: dense, sparse, and ColBERT vectors.","language":"Jupyter Notebook","stars":42,"topics":["bge-m3","csharp","dotnet","embedding-models","inference","java","machine-learning","onnx","python","pytorch"],"license":"Apache-2.0","category":"machine-learning","readme_excerpt":"BGE-M3 ONNX This repository demonstrates how to convert the complete BGE-M3 model to ONNX format and use it in multiple programming languages with full multi-vector functionality . Key Features - Generate all three BGE-M3 embedding types: dense, sparse, and ColBERT vectors - Reduced latency with local embedding generation - Full control over the embedding pipeline with no external dependencies - Works offline without internet connectivity requirements - Cross-platform compatibility (C#, Java, Python) - CUDA GPU acceleration support Repository Structure - bge-m3-to-onnx.ipynb - Jupyter notebook demonstrating the BGE-M3 conversion process - /samples/dotnet - C# implementation - /samples/java - Java implementation - /samples/python - Python implementation - generate reference embeddings.py - Script to generate reference embeddings for cross-language testing - run tests.sh and run tests.ps1 - Test scripts for Linux/macOS and Windows Getting Started 1. Clone this repository: 2. Get the BGE-M3 ONNX models: - Option 1: Download from releases (recommended) - Check the repository releases and download onnx.zip - It already contains the bge-m3 embedding model and its tokenizer - Option 2: Generate yourself using the notebook - Open and run bge-m3-to-onnx.ipynb - this is the most important file in the repository - The notebook demonstrates how to convert BGE-M3 from FlagEmbedding to ONNX format - This will create bge m3 tokenizer.onnx , bge m3 model.onnx , and bge m3 model.onnx data in ","default_branch":null,"files":null,"tree":[],"storefront":"/r/yuniko-software","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/yuniko-software/bge-m3-onnx/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}