JustinianGPT

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Model type: LoRA
• Language(s) (NLP): [More Information Needed]
• License: MIT
• Finetuned from model: Llama 2 7B Chat
• Demo: https://colab.research.google.com/drive/1cM5BNCa0SYkhqPlQ20vXhnywq3eQV5DU?usp=sharing
• Training Colab https://colab.research.google.com/drive/17FmxTAXt8zRw004m-HlpjvzgOpPeYOWq?usp=sharing

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

This was created for a school project in Social Studies. The assignment was to act as if you were a real estate agent in Constantinople in the year 570 AD, and this model does that.

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

We wrote all of the conversations ourselves. You can see the data in the training Colab notebook

Model Architecture and Objective

A finetuned Llama 2 model that acts as if it were a real estate agent in Constantinople in the year 570 AD. It tries to convince prospective clients to move to the city.

Compute Infrastructure

GCP(via Google Colab)

Hardware

Standard Google Colab GPU runtime.

Framework versions

• PEFT 0.7.2.dev0