---
base_model:
- ibm-granite/granite-embedding-reranker-english-r2
---
# ONNX Model

Converted from: granite-embedding-reranker-english-r2

## Files
- model.onnx - FP32 version
- model_quantized.onnx - INT8 quantized version
- *.json - tokenizer and config files

## Usage
```python
from transformers import AutoTokenizer
import onnxruntime as ort

tokenizer = AutoTokenizer.from_pretrained("granite-onnx")
session = ort.InferenceSession("granite-onnx/model_quantized.onnx")
```