Update README.md

README.md

@@ -14,7 +14,7 @@ widget:
 # kgourgou/bert-base-uncased-QA-classification
 
 An experiment into classifying whether a pair of (question, answer) is valid. This is not a very good model at this point, but eventually such a
-model could help with RAG. For a more appropriate model, check this one by [vectara](vectara/hallucination_evaluation_model).
+model could help with RAG. For a stronger model, check this one by [vectara](https://huggingface.co/vectara/hallucination_evaluation_model).
 
 Input must be formatted as 
 
@@ -31,8 +31,8 @@ The output probabilities are for
 
 Examples: 
 
-- "question: What number comes after five? answer: four" -> this should be class 1 as the answer is a number (even if it's not the right number).
-- "question: Which person is associated with Kanye West? answer: a tree" -> this should be class 0 as a tree is not a person.
+- "question: What number comes after five? answer: four" → this should be class 1 as the answer is a number (even if it's not the right number).
+- "question: Which person is associated with Kanye West? answer: a tree" → this should be class 0 as a tree is not a person.
 
 
 ## Base model details