Model Card for GrabbeAI

GrabbeAI is an advanced AI model based on the powerful Google Gemma 2 architecture. It is specifically trained to provide visitors of the school's website with straightforward information about the institution and answer a wide range of questions related to daily school life.

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: Finn Busse, Maximilian von Beck
  • Trained by: Finn Busse, Evan Charter, Raphael Scheimann
  • Shared by: Grabbe-Gymnasium Detmold, Dr. Claus Hilbing
  • Model Card written by: ChatGPT
  • Model type: AI chatbot
  • Language(s) (NLP): German, English, Ukrainian
  • License: Gemma Terms of Use
  • Finetuned from model: gemma-2-9b

Training Data

https://huggingface.co/datasets/grabbe-gymnasium-detmold/grabbeai

Results

GrabbeAI now serves as an AI chatbot tool on the Grabbes website.

How to Get Started with the Model

  1. Download Ollama from https://ollama.com/download
  2. Install Ollama
  3. Open the Terminal and type ollama run grabbe-gymnasium/grabbe-ai

Riscs

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Software

GrabbeAI can be used with Ollama. GrabbeAI was trained using Google Colab using Unsloth.

Model Card Author

ChatGPT

Model Card Contact

Grabbe-Gymnasium Detmold, Germany

Downloads last month
433
GGUF
Model size
9.24B params
Architecture
gemma2

4-bit

8-bit

16-bit

Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train grabbe-gymnasium-detmold/grabbe-ai

Spaces using grabbe-gymnasium-detmold/grabbe-ai 2

Collection including grabbe-gymnasium-detmold/grabbe-ai