ONNX Quantized versions of intfloat/e5-small-v2

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

Usage

from sentence_transformers import SentenceTransformer

# Load Int8 model (ARM64 example)
model = SentenceTransformer(
    "jrc2139/e5-small-v2-ONNX",
    backend="onnx",
    model_kwargs={"file_name": "onnx/model_q4.onnx"},
    trust_remote_code=True
)

Downloads last month: 20

Model tree for jrc2139/e5-small-v2-ONNX

Base model

intfloat/e5-small-v2

Quantized

(15)

this model