Update readme

README.md

@@ -2,13 +2,11 @@
 license: mit
 language:
 - el
+pipeline_tag: fill-mask
 ---
-# Logion: Machine Learning for Greek Philology
+# Logion base model
 
-BERT model trained on largest set of Ancient Greek texts to-date.
-Read the ALP paper on [here](https://aclanthology.org/2023.alp-1.20/).
-
-Trained using WordPiece tokenizer (vocab size of 50,000) on a corpus of 70+ million words in pre-modern Greek.
+BERT-based model pretrained on largest set of pre-modern Greek to-date (70+ million words). It was introduced in this [paper](https://aclanthology.org/2023.alp-1.20/). This model ignores cases and accents/diacritics.
 
 ## How to use