Update README.md

README.md

@@ -45,17 +45,16 @@ inputs = tokenizer_in([sample], return_tensors="pt")
 outputs = model.generate(**inputs)
 
 print(f"Gold answer: {gold_answer}")
-print( "            " + tokenizer_out.decode(outputs[0]))
+print("             " + tokenizer_out.decode(outputs[0], skip_special_tokens=True))
 ```
 
 ```
 Gold answer: SELECT ?obj WHERE { wd:Q42168 p:P1082 ?s . ?s ps:P1082 ?obj . ?s pq:P585 ?x filter(contains(YEAR(?x),'2013')) }
-            <pad> SELECT?obj WHERE { wd:Q4754 p:P1082?s.?s ps:P1082?obj.?s pq:P585?x filter(contains(YEAR(?x),'2013')) }
+             SELECT?obj WHERE { wd:Q4754 p:P1082?s.?s ps:P1082?obj.?s pq:P585?x filter(contains(YEAR(?x),'2013')) }
 ```
 
 Common errors include:
 
-- Adding a `<pad>` token at the beginning
 - A stray closed curly brace at the end
 - One of subject / predicate / object is wrong, while the other two are correct