vividsd/gpt2-enrondataset

This notebook finetunes GPT2 on a sample of the Enron emails dataset The dataset is publically available (you can find it in here: https://www.kaggle.com/datasets/wcukierski/enron-email-dataset)

At the end, I built a gradio interface to chat with the fine tuned model, you can ask questions to the dataset :)