updated tokenizer with config

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<CLS>",
+  "mask_token": "<MASK>",
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "unk_token": "<UNK>"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<CLS>",
+  "do_lower_case": true,
+  "mask_token": "<MASK>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sep_token": "<SEP>",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "<UNK>"
+}