Instructions to use Retr0REG/gguf-ssti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Retr0REG/gguf-ssti with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Retr0REG/gguf-ssti") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Retr0REG/gguf-ssti", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Retr0REG/gguf-ssti 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 Retr0REG/gguf-ssti # Run inference directly in the terminal: llama cli -hf Retr0REG/gguf-ssti
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Retr0REG/gguf-ssti # Run inference directly in the terminal: llama cli -hf Retr0REG/gguf-ssti
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 Retr0REG/gguf-ssti # Run inference directly in the terminal: ./llama-cli -hf Retr0REG/gguf-ssti
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 Retr0REG/gguf-ssti # Run inference directly in the terminal: ./build/bin/llama-cli -hf Retr0REG/gguf-ssti
Use Docker
docker model run hf.co/Retr0REG/gguf-ssti
- LM Studio
- Jan
- vLLM
How to use Retr0REG/gguf-ssti with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Retr0REG/gguf-ssti" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Retr0REG/gguf-ssti", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Retr0REG/gguf-ssti
- SGLang
How to use Retr0REG/gguf-ssti with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Retr0REG/gguf-ssti" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Retr0REG/gguf-ssti", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Retr0REG/gguf-ssti" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Retr0REG/gguf-ssti", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use Retr0REG/gguf-ssti with Ollama:
ollama run hf.co/Retr0REG/gguf-ssti
- Unsloth Studio
How to use Retr0REG/gguf-ssti 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 Retr0REG/gguf-ssti 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 Retr0REG/gguf-ssti to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Retr0REG/gguf-ssti to start chatting
- Docker Model Runner
How to use Retr0REG/gguf-ssti with Docker Model Runner:
docker model run hf.co/Retr0REG/gguf-ssti
- Lemonade
How to use Retr0REG/gguf-ssti with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Retr0REG/gguf-ssti
Run and chat with the model
lemonade run user.gguf-ssti-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Delete retr0reg.gguf
Why?
dude stop with the maslicious code, bro. Nobody wants it, actually. Maybe you might be doing this because you are an ML security researcher but, you should be researching, not spreading it.
Stop making any PR under this repository, please:
- This vulnerability is patched almost 2 years ago, we worked abetlen author of llama-cpp-python on addressing this issue, a patch was merged after a day of discovering this issue.
- This code is either malicious to intended to be, if you actually try understanding what it's doing. Huggingface's format security scanner (I worked with ProtectAI) actually references file like this while building it to prevent more attackers exploiting such vulnerability.
- The security advisory of this CVE-2024-34359 and many other write-ups contains the reproduction of this vulnerability.
Thank you purposing this I understand you're doing this with a good intention, but clearly you might want to 1. change the way you're communicating 2. do more background research. Thanks.
Listen, I am so sorry for the misunderstanding. I saw the code and reacted out of concern without researching the context of this repository first. It was unprofessional of me to say you should be 'researching, not spreading it'—I clearly didn't have the full picture, and I regret the tone. I appreciate you explaining the file's role in the Llama-cpp-python patch and its use for ProtectAI and Hugging Face's security scanners.
I'll be much more thorough and objective in my research before opening PRs in the future. Thanks for the correction.
It’s cool - like I said I understand you came from a good cause.