yuniko-software/bge-m3-onnx

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.

48
/ 100
Emerging

Converts the BGE-M3 model to ONNX Runtime format with optional CUDA GPU acceleration, enabling offline inference with zero external dependencies. Includes cross-language test suites to verify embedding consistency across C#, Java, and Python implementations. Supports both CPU and GPU execution paths through unified factory APIs for straightforward deployment across different deployment targets.

No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

30

Forks

5

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yuniko-software/bge-m3-onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.