jpohhhh/MiniLM-L6-v2-optimum-embeddings

By jpohhhh · ↓ 2 · ♥ 1 · Updated 2023-07-06

What's in this repo

This page lists the files in jpohhhh/MiniLM-L6-v2-optimum-embeddings, including model-optimized.onnx, model-quantized.onnx, model.onnx.

3 ONNX models (.onnx files)
13 files, including 4 .json, 3 .onnx, 2 .txt, 1 .md, 1 .ipynb, 1 .py
Last updated 2023-07-06

ONNX files

File	Size	Download
model-optimized.onnx	—	Download
model-quantized.onnx	—	Download
model.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

This repository is a fork of philschmid/all-MiniLM-L6-v2-optimum-embeddings. My own ONNX conversion seems to be about 4x slower, no discernable reason why: the quantized models seem roughly the same. The idea here is by forking we can ex. upgrade the Optimum lib used as well.

Model info

generic

generic onnx bert sentence-embeddings endpoints-template optimum license:mit endpoints_compatible region:us

↓ 2 ♥ 1

Created: 2023-07-06

Updated: 2023-07-06

View on Hugging Face

Files (13)

.gitattributes

README.md

config.json

convert.ipynb

handler.py

model-optimized.onnx ONNX

model-quantized.onnx ONNX

model.onnx ONNX

requirements.txt

special_tokens_map.json

tokenizer.json

tokenizer_config.json

vocab.txt

Related models

More models

No task type declared.