You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Intel Neural Compressor Layer-Wise Benign PoC

This repository contains a benign PyTorch checkpoint file used for security validation.

File:

Purpose:

Demonstrate that a pickle-backed PyTorch checkpoint can trigger a harmless reducer when processed by the vendored layer-wise unpickler in Intel Neural Compressor.
The reducer only writes a benign marker string during local validation.

Notes:

This is a non-weaponized proof of concept for coordinated vulnerability disclosure.
The file is intended for security triage only.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support