Downloads · 30 days
829
24% of all-time downloads
tooape/granite-embedding-97m-multilingual-r2-GBQ4-ONNX
granite-embedding-97m-multilingual-r2-GBQ4-ONNX is a feature extraction model from tooape. Use it when you need embeddings to search or compare text. It is set up for transformers.js. The card lists the license as apache-2.0.
ONNX export of ibm-granite/granite-embedding-97m-multilingual-r2 for transformers.js / onnxruntime-web, sized for in-browser retrieval (61.2 MB):
Downloads · 30 days
829
24% of all-time downloads
All-time downloads
3.5K
Public
Repo size
86.6 MB
Likes
1
Public
Click a slice to open those files.
.onnx61.2 MB · 71%
From the Hugging Face model README
ONNX export of ibm-granite/granite-embedding-97m-multilingual-r2 for transformers.js / onnxruntime-web, sized for in-browser retrieval (61.2 MB):
GatherBlockQuantized int4,
quant_axes=("Gather", 1) — runs natively on the WebGPU EP (ORT ≥ 1.23);
plain int8 Gather has no WebGPU kernel and falls back to WASM.MatMulNBitsQuantizer
with op_types_to_quantize=("MatMul", "Gather"), opset 21.Outputs token_embeddings / sentence_embedding; use pooling: 'cls',
normalize: true (the model is CLS-pooled, symmetric — no query/doc prompts).
Quantization relevance gate (vs fp32, graded nDCG@10 on private retrieval corpora + Belebele): English ±0.003; Belebele dense −0.005 (en) … −0.021 (ko), multilingual advantage over English-only siblings fully intact.
import { pipeline } from '@huggingface/transformers';
const extractor = await pipeline('feature-extraction',
'tooape/granite-embedding-97m-multilingual-r2-GBQ4-ONNX',
{ device: 'webgpu', dtype: 'q4' });
const v = await extractor('search query', { pooling: 'cls', normalize: true });