call tokenizer directly

The instructions call the tokenizer from `self.tokenizer`. Looks like this is some kind of copy/paste error. Simple fix is to call the tokenizer that was initialized directly

README.md

@@ -123,7 +123,7 @@ papers = [{'title': 'BERT', 'abstract': 'We introduce a new language representat
 # concatenate title and abstract
 text_batch = [d['title'] + tokenizer.sep_token + (d.get('abstract') or '') for d in papers]
 # preprocess the input
-inputs = self.tokenizer(text_batch, padding=True, truncation=True,
+inputs = tokenizer(text_batch, padding=True, truncation=True,
                                    return_tensors="pt", return_token_type_ids=False, max_length=512)
 output = model(**inputs)
 # take the first token in the batch as the embedding