Update README.md

README.md

@@ -17,14 +17,13 @@ widget:
 <!-- Provide a quick summary of what the model is/does. -->
 
 This is the first model for Named Entity Recognition (NER) in the Moroccan dialect (Darija). The model was trained on the very first NER dataset in Darija, DarNERcorp, that can be found on Mendeley https://data.mendeley.com/datasets/286sss4k9v/4. 
-The model was trained by finetuning AraBERT on a mixed dataset composed of DarNERcorp and ANERcorp. 
 
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
 - **Developed by:** Hanane Nour Moussa
-- **Model type:** Finetuned AraBERT model for NER
+- **Model type:** Token classification
 - **Language(s) (NLP):** Arabic, Darija
 
 ### Model Sources 
@@ -34,10 +33,6 @@ The model was trained by finetuning AraBERT on a mixed dataset composed of DarNE
 - **Repository:** https://github.com/HananeNourMoussa/darija-ner (private for the time being)
 - **Paper (dataset):** Hanane Nour Moussa, Asmaa Mourhir, DarNERcorp: An annotated named entity recognition dataset in the Moroccan dialect, Data in Brief
 
-#### Training Hyperparameters
-
-The model was trained for 5 epochs using a learning rate of 3e-5 for BERT and 1e-4 for the classifier. BERT hidden dropout was set to 0.3. 
-
 #### Metrics
 
 <!-- These are the evaluation metrics being used, ideally with a description of why. -->