Instructions to use salvepilo/llama-cpp-scores-oob-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use salvepilo/llama-cpp-scores-oob-poc with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="salvepilo/llama-cpp-scores-oob-poc",
	filename="poc_scores_oob.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use salvepilo/llama-cpp-scores-oob-poc with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf salvepilo/llama-cpp-scores-oob-poc
# Run inference directly in the terminal:
llama-cli -hf salvepilo/llama-cpp-scores-oob-poc

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf salvepilo/llama-cpp-scores-oob-poc
# Run inference directly in the terminal:
llama-cli -hf salvepilo/llama-cpp-scores-oob-poc

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf salvepilo/llama-cpp-scores-oob-poc
# Run inference directly in the terminal:
./llama-cli -hf salvepilo/llama-cpp-scores-oob-poc

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf salvepilo/llama-cpp-scores-oob-poc
# Run inference directly in the terminal:
./build/bin/llama-cli -hf salvepilo/llama-cpp-scores-oob-poc

Use Docker

docker model run hf.co/salvepilo/llama-cpp-scores-oob-poc

LM Studio
Jan
Ollama
How to use salvepilo/llama-cpp-scores-oob-poc with Ollama:
```
ollama run hf.co/salvepilo/llama-cpp-scores-oob-poc
```

Unsloth Studio

How to use salvepilo/llama-cpp-scores-oob-poc with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for salvepilo/llama-cpp-scores-oob-poc to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for salvepilo/llama-cpp-scores-oob-poc to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for salvepilo/llama-cpp-scores-oob-poc to start chatting

Docker Model Runner
How to use salvepilo/llama-cpp-scores-oob-poc with Docker Model Runner:
```
docker model run hf.co/salvepilo/llama-cpp-scores-oob-poc
```

Lemonade

How to use salvepilo/llama-cpp-scores-oob-poc with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull salvepilo/llama-cpp-scores-oob-poc

Run and chat with the model

lemonade run user.llama-cpp-scores-oob-poc-{{QUANT_TAG}}

List all available models

lemonade list

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

Check out the documentation for more information.

llama-cpp-scores-oob-poc

Heap Buffer Over-Read via Mismatched Tokenizer Array Lengths in GGUF

This repository contains a proof-of-concept (PoC) demonstrating a heap buffer over-read vulnerability in llama.cpp caused by mismatched tokenizer array lengths in a crafted GGUF model file.

Vulnerability Summary

When loading a GGUF model, llama.cpp reads tokenizer metadata arrays (such as token scores and token types) and assumes their lengths match the vocabulary size. A specially crafted GGUF file can provide arrays with fewer elements than the declared vocabulary size, causing llama.cpp to read beyond the bounds of the allocated heap buffer when accessing token scores.

This results in a heap buffer over-read, which may lead to information disclosure or a crash.

Files

File	Description
`poc_scores_oob.gguf`	Crafted GGUF model file that triggers the vulnerability
`poc_scores_oob.py`	Python script used to generate the malicious GGUF file

Reproduction

# Build llama.cpp, then run with the crafted model:
./llama-cli -m poc_scores_oob.gguf -p "test"

Disclaimer

This PoC is provided for security research and responsible disclosure purposes only. Do not use it for malicious purposes.

Downloads last month: 15

GGUF

Model size

74.3k 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