jrc2139/granite-embedding-reranker-english-r2-ONNX
By jrc2139 · ↓ 1 · ♥ 0 · Updated 2026-01-16
What's in this repo
This page lists the files in jrc2139/granite-embedding-reranker-english-r2-ONNX, including model.onnx, model_qint4.onnx, model_qint8_arm64.onnx and more.
- 6 ONNX models (.onnx files)
- 12 files, including 6 .onnx, 4 .json, 1 .md
- Last updated 2026-01-16
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | — | Download |
| onnx/model_qint4.onnx | — | Download |
| onnx/model_qint8_arm64.onnx | — | Download |
| onnx/model_qint8_avx512.onnx | — | Download |
| onnx/model_qint8_avx512_vnni.onnx | — | Download |
| onnx/model_quint8_avx2.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 Quantized versions of ibm-granite/granite-embedding-reranker-english-r2
This repository contains ONNX export and multiple quantized versions of ibm-granite/granite-embedding-reranker-english-r2.
Usage
from sentence_transformers import CrossEncoder
# Load Int8 model (ARM64 example)
model = CrossEncoder(
"jrc2139/granite-embedding-reranker-english-r2-onnx",
backend="onnx",
model_kwargs={"file_name": "onnx/model_qint8_arm64.onnx"},
trust_remote_code=True
)
scores = model.predict([("Query", "Document")])
Model info
text-classification
sentence-transformers
sentence-transformers
onnx
modernbert
text-classification
transformers
onnxruntime
reranker
int8
int4
base_model:ibm-granite/granite-embedding-reranker-english-r2
base_model:quantized:ibm-granite/granite-embedding-reranker-english-r2
text-embeddings-inference
↓ 1
♥ 0
Created: 2025-12-09
Updated: 2026-01-16
View on Hugging FaceFiles (12)
.gitattributes
README.md
config.json
onnx/model.onnx
ONNX
onnx/model_qint4.onnx
ONNX
onnx/model_qint8_arm64.onnx
ONNX
onnx/model_qint8_avx512.onnx
ONNX
onnx/model_qint8_avx512_vnni.onnx
ONNX
onnx/model_quint8_avx2.onnx
ONNX
special_tokens_map.json
tokenizer.json
tokenizer_config.json