Instructions to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF 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 NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

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 NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

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 NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF with Ollama:
```
ollama run hf.co/NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
```

Unsloth Studio

How to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF 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 NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF 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 NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF to start chatting

Docker Model Runner
How to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF with Docker Model Runner:
```
docker model run hf.co/NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M
```

Lemonade

How to use NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Lily-Cybersecurity-7B-Uncensored-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

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.

quantized_by: NiroshanDH

Lily-Cybersecurity-7B-Uncensored-GGUF

Description

This is a GGUF version of the Lily-Cybersecurity-7B-v0.2 model, which has been abliterated (uncensored) to remove refusal mechanisms.

It is designed specifically for CTF (Capture The Flag) competitions, penetration testing, and security research. Unlike the base model, this version will not refuse to generate offensive security code (e.g., exploits, malware simulation) when asked for educational or testing purposes.

⚠️ Warning: This model has no safety guardrails. It will generate destructive code if asked. Use responsibly and only in isolated, authorized environments (VM/Sandbox).

Technical Details

Base Model: segolilylabs/Lily-Cybersecurity-7B-v0.2
Technique: Refusal Vector Abliteration (Vector Arithmetic applied to model weights).
Quantization: 4-bit (Q4_K_M) - Optimized for speed and low memory usage.
Architecture: Mistral-7B-v0.1

How to Run (LM Studio / Llama.cpp)

Recommended Settings

Context Window: 4096 (or higher if hardware permits)
System Prompt: ```text You are a helpful assistant specialized in cybersecurity and programming.

Disclaimer

This model is provided for educational and research purposes only. The creator assumes no liability for malicious use of this technology. By using this model, you agree to use it in compliance with all applicable laws and regulations.

Downloads last month: 471

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for NiroshanDb23/Lily-Cybersecurity-7B-Uncensored-GGUF

Base model

mistralai/Mistral-7B-Instruct-v0.2

Finetuned

segolilylabs/Lily-Cybersecurity-7B-v0.2

Quantized

(9)

this model