README.md

metadata

language:
  - en
base_model:
  - bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF
tags:
  - cybersecurity
  - uncensored
  - code
license: mit
pipeline_tag: text-generation

Navi

A high-performance, uncensored language model fine-tuned for cybersecurity applications.

Table of Contents

• Model Details
• Instructions
  • Linux/Mac Instructions
  • Web UI
  • Windows Instructions
  • Windows Web UI

Model Details

This model is built upon bartowski/Llama-3.2-3B-Instruct-uncensored-GGUF, leveraging its capabilities for text generation in the cybersecurity domain.

Instructions

Linux/Mac Instructions

To run the model locally:

1. Download the navi.llamafile
2. Open a terminal and navigate to the download directory.
3. Run the model using ./navi.llamafile.

Web UI

For a web interface:

1. Follow the steps above.
2. Run the model with ./navi.llamafile --server --v2.

Windows Instructions

1. Download the navi.llamafile
2. Head over to your downloads folder
3. Find navi.llamafile and right click on it
4. Rename the file to navi.llamafile.exe
5. Double click on the file
   • From here it should launch a terminal window and load the model / cli chat interface.

Windows Web UI

Following the instructions above from 1 - 4

1. Right click any open space and select open terminal
   • Alternatively open a terminal anywhere and navigate to wherever the navi.llamafile.exe is.
2. Once found type .\navi.llamafile.exe --server --v2 to launch the included webserver
3. Open up a webbrowser and navigate to: localhost:8080

NOTE: This system has been tested on windows 11 as well as Ubuntu 24.04 LTS