Use the DistilBertTokenizer for this DistilBERT-based model

README.md

@@ -88,7 +88,7 @@ query = "What's the weather in ny now?"
 document = "Currently New York is rainy."
 
 # encode the query & document
-feature = tokenizer([query, document], padding=True, truncation=True, return_tensors='pt', return_token_type_ids=False)
+feature = tokenizer([query, document], padding=True, truncation=True, return_tensors='pt')
 output = model(**feature)[0]
 sparse_vector = get_sparse_vector(feature, output)
 

tokenizer_config.json

@@ -8,6 +8,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }