granite-embedding-97m-multilingual-r2-ONNX

philipp-zettl/granite-embedding-97m-multilingual-r2-ONNX

This model was converted to ONNX format from ibm-granite/granite-embedding-97m-multilingual-r2 using optimum via the WebGPU Export My Repo space.

Refer to the original model card for more details on the model.

Available Quantizations

• q4
• q8
• q4f16

Use with Transformers.js

import { pipeline } from '@huggingface/transformers';

const pipe = await pipeline('feature-extraction', 'philipp-zettl/granite-embedding-97m-multilingual-r2-ONNX', {
  dtype: 'q4',  // or: q4, q8, q4f16
});