Downloads · 30 days
6
2% of all-time downloads
princeton-logion/logion-bert-ate
logion-bert-ate is a fill-mask model from princeton-logion. Use it when you need the model to fill a missing word. The card lists the license as mit.
Logion Base BERT model fine-tuned to Aristotle, Theophrastus, and Eudlic texts.
Downloads · 30 days
6
2% of all-time downloads
All-time downloads
290
Public
Parameters
124M
1.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt996 MB · 67%
From the Hugging Face model README
Logion Base BERT model fine-tuned to Aristotle, Theophrastus, and Eudlic texts.
Fine-tuned for mask-filling on a set of 1.5+ million words (all of Theophrastus, Euclid, and Aristotle, minus De lineis insecabilibus).
Requirements:
pip install transformers
Load the model and tokenizer directly from the HuggingFace Model Hub:
from transformers import BertTokenizer, BertForMaskedLM
tokenizer = BertTokenizer.from_pretrained("princeton-logion/logion-bert-ate")
model = BertForMaskedLM.from_pretrained("princeton-logion/logion-bert-ate")
If you use this model in your research, please cite the repo.