Update README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
-- generated_from_trainer
+- grc, Fill-Mask, PyTorch, bert, Token Classification
+language:
+- grc
 model-index:
 - name: aristoBERTo
   results: []
@@ -11,26 +13,21 @@ widget:
 
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
 
 # aristoBERTo
 
-This model is a fine-tuned version of [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on the Ancient Greek dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6323
-
-## Model description
+aristoBERTo is a pre-trained model for ancient Greek, a low resource  language. We initialized the pre-training with weights from [GreekBERT](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1), a Greek version of BERT pre-trained on a large corpus of modern Greek (~ 30 GB of texts). We continued the pre-training with an ancient Greek corpus of about 900 MB, which was scrapped from the web and post-processed. Duplicate texts and editorial punctuation were removed. 
 
-More information needed
+Applied to the processing of ancient Greek, aristoBERTo outperforms xlm-roberta-base and mdenberta in most downstream fine-tuning tasks like the labeling of POS, MORPH, DEP and LEMMA. aristoBERTo is provided by the Diogenet project of the University of California, San Diego. 
+ 
 
-## Intended uses & limitations
+## Intended uses
 
-More information needed
+This model was created for fine-tuning with spaCy and the Universal Dependency datasets for ancient Greek and a NER annotated corpus produced by the Diogenet project. 
 
-## Training and evaluation data
 
-More information needed
+It achieves the following results on the evaluation set:
+- Loss: 1.6323
 
 ## Training procedure