A simple model fine tuning pipe line for text generation using GPT-2
- Python 3.11
- pipenv
- pytorch
If you don't have pipenv installed, you can install it using pip:
pip install pipenv
git clone https://github.com/MehdiZare/healthai
cd healthai
pipenv install
You need to set the API_KEY
to the API key for accessing mediastack. It can be saved in a .env
file in the root of the project.
Use training notebook to train the model and then use the inference notebook to generate text.
Model weights are too large to be saved in the repo. You can download the weight folder from here and put it in the root folder.