Downloads · 30 days
25.1K
16% of all-time downloads
gaunernst/bert-mini-uncased
bert-mini-uncased is a fill-mask model from gaunernst. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
Mini BERT models from https://arxiv.org/abs/1908.08962 that the HF team didn't convert. The original conversion script is used.
Downloads · 30 days
25.1K
16% of all-time downloads
All-time downloads
154K
Public
Parameters
11.3M
90.2 MB on disk
Likes
0
Public
Click a slice to open those files.
.bin45.1 MB · 50%
How the weights are stored.
F3211.3M · 100%
From the Hugging Face model README
Mini BERT models from https://arxiv.org/abs/1908.08962 that the HF team didn't convert. The original conversion script is used.
See the original Google repo: google-research/bert
Note: it's not clear if these checkpoints have undergone knowledge distillation.
See other BERT model cards e.g. https://huggingface.co/bert-base-uncased
@article{turc2019,
title={Well-Read Students Learn Better: On the Importance of Pre-training Compact Models},
author={Turc, Iulia and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1908.08962v2 },
year={2019}
}