We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense autoregressive model that has publicly available weights at the time of submission. In this work, we describe \model{}'s architecture and training and evaluate its performance on a range of language-understanding, mathematics, and knowledge-based tasks. We find that GPT-NeoX-20B is a particularly powerful few-shot reasoner and gains far more in performance when evaluated five-shot than similarly sized GPT-3 and FairSeq models. We open-source the training and evaluation code, as well as the model weights, at https://github.com/EleutherAI/gpt-neox.
Cite
@article{arxiv.2204.06745,
title = {GPT-NeoX-20B: An Open-Source Autoregressive Language Model},
author = {Sid Black and Stella Biderman and Eric Hallahan and Quentin Anthony and Leo Gao and Laurence Golding and Horace He and Connor Leahy and Kyle McDonell and Jason Phang and Michael Pieler and USVSN Sai Prashanth and Shivanshu Purohit and Laria Reynolds and Jonathan Tow and Ben Wang and Samuel Weinbach},
journal= {arXiv preprint arXiv:2204.06745},
year = {2022}
}
Comments
To appear in the Proceedings of the ACL Workshop on Challenges & Perspectives in Creating Large Language Models