Instructions to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="dxoth1nh/poc-llama-cpp-chat-template-recursion-dos",
	filename="macro-recursion.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
# Run inference directly in the terminal:
llama cli -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
# Run inference directly in the terminal:
llama cli -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

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 dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
# Run inference directly in the terminal:
./llama-cli -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

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 dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
# Run inference directly in the terminal:
./build/bin/llama-cli -hf dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

Use Docker

docker model run hf.co/dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

LM Studio
Jan
Ollama
How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with Ollama:
```
ollama run hf.co/dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
```

Unsloth Studio

How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos 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 dxoth1nh/poc-llama-cpp-chat-template-recursion-dos 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 dxoth1nh/poc-llama-cpp-chat-template-recursion-dos to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dxoth1nh/poc-llama-cpp-chat-template-recursion-dos to start chatting

Atomic Chat new
Docker Model Runner
How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with Docker Model Runner:
```
docker model run hf.co/dxoth1nh/poc-llama-cpp-chat-template-recursion-dos
```

Lemonade

How to use dxoth1nh/poc-llama-cpp-chat-template-recursion-dos with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dxoth1nh/poc-llama-cpp-chat-template-recursion-dos

Run and chat with the model

lemonade run user.poc-llama-cpp-chat-template-recursion-dos-{{QUANT_TAG}}

List all available models

lemonade list

poc-llama-cpp-chat-template-recursion-dos / README.md

dxoth1nh

Add gated GGUF chat-template recursion PoC

e30a856 verified 9 days ago

preview code

Raw

History Blame Contribute Delete

931 Bytes

	---
	license: other
	tags:
	- gguf
	- security
	- huntr
	- llama-cpp
	---

	# Gated security PoC artifact

	Proof-of-concept artifact for a responsibly disclosed model file vulnerability report.

	Format: GGUF (`.gguf`)

	This repository is for defensive validation and triage only. It is not a usable model. Do not request access unless you are the assigned reviewer.

	Contents:
	- `macro-recursion.gguf`: crafted artifact
	- `replay_llama_completion.py`: bounded reproduction script for `llama-completion`
	- `build-meta.json`: local validation metadata and hashes

	Expected reviewer flow:
	1. Download the artifact into an isolated environment.
	2. Build or provide `llama-completion` from the tested `llama.cpp` revision.
	3. Run:

	```bash
	python3 replay_llama_completion.py --completion-bin /path/to/llama-completion
	```

	Expected result:
	- the process terminates with `SIGSEGV` (`returncode` `139`) while handling the embedded chat template.