Added usage instructions

README.md

@@ -8,7 +8,14 @@ tags:
 
 
 
-An ELECTRA-small model for Ancient Greek, trained on texts from Homer up until the 4th century AD.
+An ELECTRA-small model for Ancient Greek, trained on texts from Homer up until the 4th century AD from the literary [GLAUx](https://github.com/alekkeersmaekers/glaux) corpus and the [DukeNLP](https://github.com/alekkeersmaekers/duke-nlp) papyrus corpus.
+
+The model has some design choices made to combat data sparsity:
+* Its input should always be in Unicode NFD (so separate Unicode signs for diacritics).
+* All grave accents should be replaced with acute accents (καί, not καὶ).
+* When a word contains two accents, the second one should be removed (εἶπε μοι, not εἶπέ μοι).
+
+If you use it in conjunction with [glaux-nlp](https://github.com/alekkeersmaekers/glaux-nlp), you can pass the tokenized sentence to normalize_tokens from tokenization.Tokenization, using normalization_rule=greek_glaux, which will do all these normalizations for you. 
 
 ## Citation