Update README.md

README.md

@@ -1,3 +1,19 @@
 ---
+language: fr        # <-- my language
+widget:
+ - text: "Ne laisse aucun résidu. Ne nécessite pas de nettoyage après l'application."
+ - text: "Nous n'avons pas d'argent et aucune relation."
+ - text: "C'est marrant comme tout le monde oublie ça, hein ?"
+ - text: "Il estaaaaaaaaaaad impr2éviswwible, oui,i,v.1 danfaagereux."
+ - text: "L'hépssasdati@!@@!te, oui, une pleaaane indemnisation."
+ - text: "Après une hééésiéétation,!!! j'ai fait signe que oui."      
+
 license: other
 ---
+This model was trained for evaluating linguistic acceptability and grammaticality. 
+
+Label_1 means ACCEPTABLE - the sentence is perfectly understandable by native speakers and has no serious grammatic and syntactic flaws.
+
+Label_0 means NOT ACCEPTABLE - the sentence is flawed both orthographically and grammatically.
+
+The model was trained on 50 thousand French sentences from the news_commentary dataset (https://huggingface.co/datasets/news_commentary). Out of 50 thousand 25 thousand sentences were algorithmically corrupted using the open source Python library https://github.com/eistakovskii/text_corruption_plus. The library was originally developed by aylliote (https://github.com/aylliote/corruption), but it was slightly adapted for the purposes of this model.