Hugging Face's logo

nixiesearch
/
multilingual-e5-large-onnx

Feature Extraction sentence-transformers ONNX
English xlm-roberta sentence-similarity Inference Endpoints
Model card Files Community
Edit model card

ONNX version of intfloat/multilingual-e5-large

This is a sentence-transformers model: It maps sentences & paragraphs to a N dimensional dense vector space and can be used for tasks like clustering or semantic search.

The model conversion was made with onnx-convert tool with the following parameters:

python convert.sh --model_id intfloat/multilingual-e5-large --quantize QInt8 --optimize 0

There are two versions of model available:

  • model.onnx - Float32 version, with optimize=0
  • model_opt0_QInt8.onnx - QInt8 quantized version, with optimize=0

Compared to the base/small versions of the model, this one is not optimized due to a bug in ONNX runtime: https://github.com/microsoft/onnxruntime/issues/15563

License

Apache 2.0

Downloads last month
3

Datasets used to train nixiesearch/multilingual-e5-large-onnx