e5-large-v2-ONNX / README.md
jrc2139's picture
Upload folder using huggingface_hub
1e712a4 verified
metadata
tags:
  - sentence-transformers
  - transformers
  - onnx
  - onnxruntime
  - reranker
  - int8
  - int4
base_model: intfloat/e5-large-v2
library_name: sentence-transformers

ONNX Quantized versions of intfloat/e5-large-v2

This repository contains ONNX export and multiple quantized versions of intfloat/e5-large-v2.

Usage

from sentence_transformers import SentenceTransformer

# Load Int8 model (ARM64 example)
model = SentenceTransformer(
    "jrc2139/e5-large-v2-ONNX",
    backend="onnx",
    model_kwargs={"file_name": "onnx/model_qint8_arm64.onnx"},
    trust_remote_code=True
)