Tiger Gemma 9 B v3

Introduction

Tiger-Gemma-9B-V3 is a decensored version of the Gemma 9B SPPO model, enhanced with a new dataset that eliminates unwanted content. The model is hosted on Hugging Face by the user TheDrummer.

Architecture

The architecture of Tiger-Gemma-9B-V3 is based on the original Gemma 9B SPPO model but has been refined to remove certain elements deemed unnecessary or undesirable.

Training

This version of the model was trained with a dataset specifically curated to filter out certain types of content, focusing on improving the model's performance and ethical alignment.

Guide: Running Locally

1. Clone the Repository: Visit the Hugging Face model page and clone the repository to your local machine.
2. Install Dependencies: Ensure that you have all the necessary libraries and dependencies installed. Use package managers like pip for Python packages.
3. Run the Model: Execute the model using a Python script or Jupyter Notebook. Ensure that your environment is set up correctly to handle the model’s requirements.
4. Cloud GPUs: For optimal performance, consider using cloud GPUs from providers like AWS, Google Cloud, or Azure, especially for large-scale inference or training.

License

The licensing details for Tiger-Gemma-9B-V3 are not specified in the provided information. Please consult the model's page on Hugging Face for specific licensing information.