nixiesearch/multilingual-e5-large-onnx

By nixiesearch · ↓ 15 · ♥ 2 · Updated 2023-11-17

What's in this repo

This page lists the files in nixiesearch/multilingual-e5-large-onnx, including model.onnx, model_opt0_QInt8.onnx.

2 ONNX models (.onnx files)
10 files, including 4 .json, 2 .onnx, 1 .md, 1 .onnx_data, 1 .model
Last updated 2023-11-17

ONNX files

File	Size	Download
model.onnx	—	Download
model_opt0_QInt8.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

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

Model info

feature-extraction sentence-transformers

sentence-transformers onnx xlm-roberta feature-extraction sentence-similarity en dataset:s2orc dataset:flax-sentence-embeddings/stackexchange_xml dataset:ms_marco dataset:gooaq dataset:yahoo_answers_topics dataset:code_search_net

↓ 15 ♥ 2

Created: 2023-11-17

Updated: 2023-11-17

View on Hugging Face

Files (10)

.gitattributes

README.md

config.json

model.onnx ONNX

model.onnx_data

model_opt0_QInt8.onnx ONNX

sentencepiece.bpe.model

special_tokens_map.json

tokenizer.json

tokenizer_config.json

Related models

More feature-extraction models

Browse all feature-extraction models