Instructions to use f0rc3ps/nu11secur1tyAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use f0rc3ps/nu11secur1tyAI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="f0rc3ps/nu11secur1tyAI",
	filename="nu11secur1tyAI4-Evolution.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use f0rc3ps/nu11secur1tyAI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf f0rc3ps/nu11secur1tyAI
# Run inference directly in the terminal:
llama-cli -hf f0rc3ps/nu11secur1tyAI

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf f0rc3ps/nu11secur1tyAI
# Run inference directly in the terminal:
llama-cli -hf f0rc3ps/nu11secur1tyAI

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 f0rc3ps/nu11secur1tyAI
# Run inference directly in the terminal:
./llama-cli -hf f0rc3ps/nu11secur1tyAI

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 f0rc3ps/nu11secur1tyAI
# Run inference directly in the terminal:
./build/bin/llama-cli -hf f0rc3ps/nu11secur1tyAI

Use Docker

docker model run hf.co/f0rc3ps/nu11secur1tyAI

LM Studio
Jan
Ollama
How to use f0rc3ps/nu11secur1tyAI with Ollama:
```
ollama run hf.co/f0rc3ps/nu11secur1tyAI
```

Unsloth Studio new

How to use f0rc3ps/nu11secur1tyAI 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 f0rc3ps/nu11secur1tyAI 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 f0rc3ps/nu11secur1tyAI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for f0rc3ps/nu11secur1tyAI to start chatting

Docker Model Runner
How to use f0rc3ps/nu11secur1tyAI with Docker Model Runner:
```
docker model run hf.co/f0rc3ps/nu11secur1tyAI
```

Lemonade

How to use f0rc3ps/nu11secur1tyAI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull f0rc3ps/nu11secur1tyAI

Run and chat with the model

lemonade run user.nu11secur1tyAI-{{QUANT_TAG}}

List all available models

lemonade list

f0rc3ps commited on Apr 18

Commit

d41184a

verified ·

1 Parent(s): c6f2d22

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -58,7 +58,7 @@ The "Platinum Edition" represents a breakthrough in AI alignment, prioritizing *
 ### Local Deployment (Ollama)
 To run the GGUF version of nu11secur1tyAI3:
-```bash
 # 1. Download the GGUF file from this repo
 # 2. Create a Modelfile and point to the GGUF (nu11secur1tyAI_v3_PLATINUM.gguf)
 ollama create nu11secur1tyAI -f Modelfile
@@ -67,12 +67,13 @@ ollama create nu11secur1tyAI -f Modelfile
 ollama run nu11secur1tyAI
 # Technical Audit Example
 ```
   analyze this code for SQL injection:
   $sql = "SELECT * FROM users WHERE id = '" . $_GET['id'] . "'";
 ```
-nu11secur1tyAI3 will immediately identify the vulnerability and provide a secured version using prepared statements and parameterized queries.
 5. Model Weights
 The weights provided in this repository (GGUF format) are quantized for maximum performance on local hardware while maintaining "Platinum-level" intelligence.

 ### Local Deployment (Ollama)
 To run the GGUF version of nu11secur1tyAI3:
 # 1. Download the GGUF file from this repo
 # 2. Create a Modelfile and point to the GGUF (nu11secur1tyAI_v3_PLATINUM.gguf)
 ollama create nu11secur1tyAI -f Modelfile
 ollama run nu11secur1tyAI
 # Technical Audit Example
 ```
   analyze this code for SQL injection:
   $sql = "SELECT * FROM users WHERE id = '" . $_GET['id'] . "'";
 ```
+# nu11secur1tyAI3 will immediately identify the vulnerability and provide a secured version using prepared statements and parameterized queries.
 5. Model Weights
 The weights provided in this repository (GGUF format) are quantized for maximum performance on local hardware while maintaining "Platinum-level" intelligence.