update

README.md

@@ -25,8 +25,8 @@ model-index:
 
 # Turkish SQuAD  Model : Question Answering
 
-I fine-tuned Loodos-Turkish-Bert-Model for Question-Answering problem with TQuAD dataset
-* Loodos-BERT-base: https://huggingface.co/loodos/bert-base-turkish-uncased
+I fine-tuned Loodos-Turkish-Bert-Model for Question-Answering problem with TQuAD dataset. Since the "loodos/bert-base-turkish-uncased" model gave the best results for the Turkish language in classification in the "Auto-tagging of Short Conversational Sentences using Transformer Methods" research we conducted with my teammates, I used this model because I thought that the success rate could be high in the question-answering.
+* Loodos-BERT-base-uncased: https://huggingface.co/loodos/bert-base-turkish-uncased
 * TQuAD dataset:  https://github.com/TQuad/turkish-nlp-qa-dataset