If you wish to download the code for creating the NumBERT model published in:
Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, and Dan Roth. 2020. Do language embeddings capture scales? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings
and a sample model checkpoint (used for experiments in the paper) please visit:
https://github.com/google-research/google-research/tree/master/numbert