---
license: mit
language:
- en
pipeline_tag: text-generation
library_name: transformers
widget:
- text: "<start>The sea at night, "
  example_title: "Example 1"
- text: "<start>So fast he pulled his sword along"
  example_title: "Example 2"
- text: "<start>Now that the trees have"  
  example_title: "Example 3"
---
# gpt2-poetry-model-crpo

This model is based on the [smallest gpt2 model](https://huggingface.co/gpt2) (137 M parameters) 
fine-tuned on the [Gutenberg Poetry Corpus](https://github.com/aparrish/gutenberg-poetry-corpus) (142 MB of text) 
for 3 epochs.

The model generates lines of poetry, in English, each of them starting with the `<start>` tag, which can be removed through post-processing.


This model was trained by [Teo Ferrari](https://www.linkedin.com/in/teo-ferrari-0a4009176/) 
as part of his Bachelor thesis at [HEIG-VD](https://gaps.heig-vd.ch/public/diplome/rapports.php?id=6763), 
supervised by [Andrei Popescu-Belis](http://iict-space.heig-vd.ch/apu/).
The model is described in "[GPoeT: a Language Model Trained for Rhyme Generation on Synthetic Data](https://aclanthology.org/2023.latechclfl-1.2/)"
and is used in the [CR-PO](https://github.com/heig-iict-ida/crpo) system for [interactive poem generation](https://aclanthology.org/2022.lrec-1.377),
along with several other models for specific topics or emotions.