Update README.md

README.md

@@ -2,7 +2,7 @@
 language: en
 tags:
 - qg
-- question 
+- question
 - generation
 - SQuAD
 - metric
@@ -23,7 +23,7 @@ widget:
 # t5-qg_squad1-en
 
 ## Model description
-This model is a *Question Generation* model based on T5-small. 
+This model is a *Question Generation* model based on T5-small.
 It is actually a component of [QuestEval](https://github.com/recitalAI/QuestEval) metric but can be used independently as it is, for QG only.
 
 
@@ -38,7 +38,7 @@ model = T5ForConditionalGeneration.from_pretrained("ThomasNLG/t5-qg_squad1-en")
 
 You can play with the model using the inference API, the text input format should follow this template (accordingly to the training stage of the model):
 
-`text_input = "sv1 <\/s> {ANSWER} <\/s> {CONTEXT}"
+`text_input = "sv1 </s> {ANSWER} </s> {CONTEXT}"`
 
 ## Training data
 The model was trained on SQuAD.