metadata
language:
- en
library_name: transformers
datasets:
- nilq/babylm-10M
- GPT-2 model trained as ablation by team CLAUSE Bielefeld for the BabyLM challenge 2023
- for more info, please check out the paper
Citation:
@inproceedings{bunzeck-zarriess-2023-gpt,
title = "{GPT}-wee: How Small Can a Small Language Model Really Get?",
author = "Bunzeck, Bastian and
Zarrie{\ss}, Sina",
editor = "Warstadt, Alex and
Mueller, Aaron and
Choshen, Leshem and
Wilcox, Ethan and
Zhuang, Chengxu and
Ciro, Juan and
Mosquera, Rafael and
Paranjabe, Bhargavi and
Williams, Adina and
Linzen, Tal and
Cotterell, Ryan",
booktitle = "Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-babylm.2",
doi = "10.18653/v1/2023.conll-babylm.2",
pages = "35--46",
}