We introduce Nemotron-4 15B, a 15-billion-parameter large multilingual language model trained on 8 trillion text tokens. Nemotron-4 15B demonstrates strong performance when assessed on English, multilingual, and coding tasks: it outperforms all existing similarly-sized open models on 4 out of 7 downstream evaluation areas and achieves competitive performance to the leading open models in the remaining ones. Specifically, Nemotron-4 15B exhibits the best multilingual capabilities of all similarly-sized models, even outperforming models over four times larger and those explicitly specialized for multilingual tasks.
Cite
@article{arxiv.2402.16819,
title = {Nemotron-4 15B Technical Report},
author = {Jupinder Parmar and Shrimai Prabhumoye and Joseph Jennings and Mostofa Patwary and Sandeep Subramanian and Dan Su and Chen Zhu and Deepak Narayanan and Aastha Jhunjhunwala and Ayush Dattagupta and Vibhu Jawa and Jiwei Liu and Ameya Mahabaleshwarkar and Osvald Nitski and Annika Brundyn and James Maki and Miguel Martinez and Jiaxuan You and John Kamalu and Patrick LeGresley and Denys Fridman and Jared Casper and Ashwath Aithal and Oleksii Kuchaiev and Mohammad Shoeybi and Jonathan Cohen and Bryan Catanzaro},
journal= {arXiv preprint arXiv:2402.16819},
year = {2024}
}