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.

GGUF Division-by-Zero PoC

This repository hosts a minimal (53-byte) proof-of-concept GGUF file used to demonstrate CWE-369 (Divide By Zero) in gguf_init_from_file() in ggml-org/llama.cpp (ggml/src/gguf.cpp).

Loading poc_divzero.gguf with an unpatched build of ggml/llama.cpp crashes the process with SIGFPE before any tensor data is read.

Submitted as part of a coordinated disclosure via huntr.com (Protect AI MFV / GGUF track). Access is gated for review purposes; this file is provided solely for vulnerability verification and must not be used to attack production systems.

Downloads last month: -

GGUF

Model size

0 params

Architecture

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