PII-Tracer, ONNX 8-bit
An ONNX version of perplexity-ai/PII-Tracer (MIT, Perplexity AI), made for Efitra, a private AI app that runs on your own computer. Efitra uses it in Private mode to find personal details and hide them before a question goes to a cloud model.
This is not a new model: same weights, exported and shrunk.
What was done
- Exported from PyTorch to ONNX (opset 18). The fp32 ONNX gives the same result as PyTorch fp32 on all 103 test texts.
- Weights quantized to 8 bits in blocks of 32 (
MatMulNBits), maths in fp32. - The vocabulary table quantized to 8 bits too (
GatherBlockQuantized), which brings the file from 2.4 GB to 680 MB.
Quality
On Efitra's 103 test texts (English, French, Spanish), compared with the original fp32 model:
- 99 of 103 identical.
- No personal detail missed.
- The 4 differences: 3 extra things hidden (a postcode-like number, a medical word, an amount) and one word ("française") no longer hidden.
Files
| File | SHA-256 |
|---|---|
pii_tracer.onnx |
ab1fd2b4cb2dced8b32ef784d0e07559984fd641566ee12b7e608ee7c45c73d2 |
pii_tracer.onnx.data |
d93b74fd12582c084e790c11224e448fc277ffc5a5739df0ab035164d4d59d37 |
tokenizer.json (unchanged from the original) |
cae14d1c8dda080f23792355b0692b826bf1f1da3c86ebc1b37548a391cf6526 |
Tested with ONNX Runtime 1.31 on CPU.
Licence
MIT, as the original. Copyright (c) 2026 Perplexity AI, Inc. See LICENSE.
Published by Malaloon Studio.
Model tree for malaloon/PII-Tracer-ONNX-Q8
Base model
perplexity-ai/PII-Tracer