Gemmasutra Mini 2 B v1

Introduction

Gemmasutra-Mini-2B-v1 is an advanced 2 billion parameter model designed to enhance role-playing (RP) experiences. It is especially tailored for use across various platforms, including browsers, mobile devices, and Raspberry Pi, providing an uncensored and unaligned interaction.

Architecture

This model is a compact yet powerful alternative to larger RP models, allowing users to enjoy sophisticated engagement without the need for high-end hardware. It is optimized for diverse environments and supports various formats, such as GGUF and ARM, for usability across different devices.

Training

Gemmasutra-Mini-2B-v1 was fine-tuned by TheDrummer to deliver superior RP performance. It is not intended for mathematical computations but excels in generating engaging dialogues and scenarios.

Guide: Running Locally

To run Gemmasutra-Mini-2B-v1 on your local machine, follow these steps:

1. Download the Model: Obtain the model from Hugging Face.
2. Choose a Platform: Ensure compatibility with your device, whether it's a browser, mobile device, or Raspberry Pi.
3. Install Required Software: Use platforms like Kobold 1.72 for PC or Layla for mobile.
4. Configure Settings: Utilize the Gemma Instruct template for optimal performance.
5. Run the Model: Execute the model locally, considering the system role modifications for the best results.

For enhanced performance, consider using cloud GPU services such as AWS, Google Cloud, or Azure, which can provide the necessary computational power.

License

Gemmasutra-Mini-2B-v1 is distributed under a non-standard license. Users must review the specific terms and conditions associated with the "other" license category to ensure compliance.