Luna AI Llama2 Uncensored

🚀 Luna AI Llama2 Uncensored

A Llama2-based chat model fine-tuned on over 40,000 long-form chat discussions.

🚀 Quick Start

This section provides a quick overview of the model and how to use it. For more detailed information, please refer to the subsequent sections.

✨ Features

• Fine-tuned on Extensive Data: "Luna AI Llama2 Uncensored" is fine-tuned on over 40,000 long-form chat discussions, enabling it to handle a wide range of chat scenarios.
• Multiple Inference Versions: There are 4bit GPTQ Version for GPU inference and GGML Version for CPU inference provided by @TheBloke.

📦 Installation

There is no specific installation steps provided in the original document.

💻 Usage Examples

Basic Usage

The model follows the Vicuna 1.1/ OpenChat format:

USER: I have difficulties in making friends, and I really need someone to talk to. Would you be my friend?

ASSISTANT: Of course! Friends are always here for each other. What do you like to do?

📚 Documentation

Model Description

“Luna AI Llama2 Uncensored” is a Llama2 based Chat model fine-tuned on over 40,000 long form chat discussions. This model was fine-tuned by Tap, the creator of Luna AI.

Model Training

The fine-tuning process was performed on an 8x a100 80GB machine. The model was trained on synthetic outputs which include multiple rounds of chats between Human & AI.

Prompt Format

The model follows the Vicuna 1.1/ OpenChat format as shown in the usage example.

Benchmark Results

Inference Versions

• 4bit GPTQ Version provided by @TheBloke - for GPU inference
• GGML Version provided by @TheBloke - For CPU inference

📄 License

This project is licensed under the CC-BY-SA-4.0 license.