Question 1

What is hacnho/gguf-add-eos-token-poc?

Accepted Answer

# GGUF add_eos_token PoC This repo is a benign security research PoC for Huntr MFV triage. Files: - `llama-spm-add-eos.gguf` - `verify_remote_poc.py` Tested trigger entrypoint: - `llama-tokenize -m --ids -p ` Behavior: - seed vocab-only GGUF uses `tokenizer.ggml.add_eos_token = false` - malicious artifact flips that metadata to `true` - ordinary prompt tokenization then silently appends the EOS token id ## Reproduction ```bash python3 verify_remote_poc.py --repo hacnho/gguf-add-eos-token-poc ``` ## Expected output delta Prompt: ```text hello world ``` Control token IDs: ```text [1, 22172, 3186] ``` Malicious token IDs: ```text [1, 22172, 3186, 2] ``` The same EOS-appending behavior also appears on: - `hello world` - `hello` ## Scanner posture Local scout observed: - `modelscan`: `No issues found` on the malicious artifact

Question 2

What license applies to hacnho/gguf-add-eos-token-poc?

Accepted Answer

License: See model card. Verify terms on Hugging Face before commercial use.

Question 3

How do I run hacnho/gguf-add-eos-token-poc locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does hacnho/gguf-add-eos-token-poc need?

Accepted Answer

Runs locally from ~0.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Model ID	hacnho/gguf-add-eos-token-poc
Author	hacnho
Pipeline	—
License	—
Base model	—
Last modified	2026-06-28T07:47:31.000Z

hacnho/gguf-add-eos-token-poc overview

Repository Files & Downloads

Model Details

Model README

GGUF add_eos_token PoC

Reproduction

Expected output delta

Scanner posture

Run hacnho/gguf-add-eos-token-poc with guIDE