Hugging Face's logo

lgessler
/
microbert-ancient-greek-mx

Feature Extraction
Transformers
PyTorch
Ancient Greek (to 1453)
bert
text-embeddings-inference
Inference Endpoints
Model card Files Community
1
lgessler commited on
Commit
b56f769
•
1 Parent(s): 64d9396

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ widget:
6
 
7
  This is a [MicroBERT](https://github.com/lgessler/microbert) model for Ancient Greek.
8
 
9
- * Its suffix is **-mx**, which means that it was pretrained using supervision from mx.
10
  * The unlabeled Ancient Greek data was taken from the [Diorisis corpus](https://figshare.com/articles/dataset/The_Diorisis_Ancient_Greek_Corpus/6187256), totaling 9,058,227 tokens.
11
  * The UD treebank [UD_Ancient_Greek-PROEIL](https://github.com/UniversalDependencies/UD_Ancient_Greek-PROIEL), v2.9, totaling 213,999 tokens, was used for labeled data.
12
 
 
6
 
7
  This is a [MicroBERT](https://github.com/lgessler/microbert) model for Ancient Greek.
8
 
9
+ * Its suffix is **-mx**, which means that it was pretrained using supervision from masked language modeling and XPOS tagging.
10
  * The unlabeled Ancient Greek data was taken from the [Diorisis corpus](https://figshare.com/articles/dataset/The_Diorisis_Ancient_Greek_Corpus/6187256), totaling 9,058,227 tokens.
11
  * The UD treebank [UD_Ancient_Greek-PROEIL](https://github.com/UniversalDependencies/UD_Ancient_Greek-PROIEL), v2.9, totaling 213,999 tokens, was used for labeled data.
12