add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"[NIL]": 30525, "[END]": 30523, "[TITLE]": 30524, "[START]": 30522, "[TYPE]": 30526}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[START]", "[END]", "[TITLE]", "[NIL]", "[TYPE]"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "clean_up_tokenization_spaces": true, "do_basic_tokenize": true, "model_max_length": 1000000000000000019884624838656, "never_split": null, "special_tokens_map_file": "../models/en_ce_medmentions/special_tokens_map.json", "name_or_path": "../models/en_ce_medmentions/", "tokenizer_class": "BertTokenizer"}