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.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

GGUF PoC (Integer Overflow + Precision Loss)

This repository contains a proof-of-concept model file for GGUF tensor metadata arithmetic flaws.

Vulnerability Summary

A crafted .gguf file can trigger integer overflow and byte-size precision loss in tensor size calculations, causing boundary corruption in reader behavior.

PoC File

gguf_boundary_overflow_first_tensor.gguf

Reproduction Outline

Load the PoC file through the vulnerable GGUF reader path.
Trigger shape-driven arithmetic mismatch in tensor size computation.
Observe boundary violation behavior in tensor reader output.

Security Impact

Incorrect tensor byte sizing from attacker-controlled metadata
Cross-tensor boundary integrity failure
Offline deterministic exploit path through model file parsing

Downloads last month: 4

GGUF

Model size

27670116.1T params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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