add tokenizer

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "a-z": 28999,
+  "covid-19": 29000,
+  "f-1": 28996,
+  "i-140": 29002,
+  "i-9": 29001,
+  "w-2": 28997,
+  "w-4": 28998
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "f-1",
+    "w-2",
+    "w-4",
+    "a-z",
+    "covid-19",
+    "i-9",
+    "i-140"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}