Downloads · 30 days
16
16% of all-time downloads
joneauxedgar/pasteproof-pii-detector-onnx
pasteproof-pii-detector-onnx is a token classification model from joneauxedgar. Use it when you need labels on individual words, such as names. It is set up for onnx. The card lists the license as mit.
Quantized ONNX version of pasteproof-pii-detector-v3 for fast browser-side inference.
Downloads · 30 days
16
16% of all-time downloads
All-time downloads
102
Public
Repo size
151 MB
Likes
0
Public
Click a slice to open those files.
.onnx151 MB · 98%
From the Hugging Face model README
Quantized ONNX version of pasteproof-pii-detector-v3 for fast browser-side inference.
| Metric | Value |
|---|---|
| Model size | ~147 MB |
| Inference time | 50-100ms (browser) |
| Accuracy | ~97% F1 (minimal loss from quantization) |
import { pipeline } from '@xenova/transformers';
const detector = await pipeline(
'token-classification',
'joneauxedgar/pasteproof-pii-detector-onnx'
);
const results = await detector('const key = "sk_live_abc123";');
console.log(results);
import * as ort from 'onnxruntime-web';
const session = await ort.InferenceSession.create('model.onnx');
// ... tokenize and run inference
model.onnx - Quantized ONNX modeltokenizer.json - Tokenizer vocabularytokenizer_config.json - Tokenizer settingsconfig.json - Model configurationspecial_tokens_map.json - Special token mappingsSee pasteproof-pii-detector-v3 for full details on entity types and training.