add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"</subj>": 50001, "<obj>": 50002, "</obj>": 50003, "<subj>": 50000}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["<subj>", "</subj>", "<obj>", "</obj>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "special_tokens_map_file": "final_tokenizer/special_tokens_map.json", "name_or_path": "final_tokenizer", "tokenizer_class": "BertTokenizer"}