Downloads · 30 days
149
7% of all-time downloads
dbmdz/bert-base-historic-english-cased
bert-base-historic-english-cased is a fill-mask model from dbmdz. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
🚨 Notice: After re-checking this model again, it seems that the model is not working very well. E.g. MLM predictions are very likely to predict [UNK] token, which is actually not good.
Downloads · 30 days
149
7% of all-time downloads
All-time downloads
2.2K
Public
Parameters
111M
1.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.bin443 MB · 30%
How the weights are stored.
F32111M · 100%
From the Hugging Face model README
🚨 Notice: After re-checking this model again, it seems that the model is not working very well. E.g. MLM predictions are very likely to predict [UNK] token, which is
actually not good.
We will update this model soon. For now, please use the bigscience-historical-texts/bert-base-blbooks-cased instead, as it was pretrained on the same corpus.