Upload tokenizer

Browse files

Files changed (5) hide show

added_tokens.json +127 -0
special_tokens_map.json +7 -0
tokenizer.json +0 -0
tokenizer_config.json +14 -0
vocab.txt +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,127 @@

+{
+  "㖭": 21128,
+  "㨂": 21129,
+  "㩒": 21130,
+  "䏙": 21131,
+  "䚗": 21132,
+  "䟕": 21133,
+  "乸": 21134,
+  "仼": 21135,
+  "冚": 21136,
+  "冧": 21137,
+  "厠": 21138,
+  "厹": 21139,
+  "吔": 21140,
+  "呔": 21141,
+  "咇": 21142,
+  "唒": 21143,
+  "唓": 21144,
+  "唞": 21145,
+  "啩": 21146,
+  "喼": 21147,
+  "嗄": 21148,
+  "嗌": 21149,
+  "嗮": 21150,
+  "嗱": 21151,
+  "嘥": 21152,
+  "噃": 21153,
+  "噉": 21154,
+  "噏": 21155,
+  "噚": 21156,
+  "嚹": 21157,
+  "嚿": 21158,
+  "囇": 21159,
+  "囯": 21160,
+  "妺": 21161,
+  "嬲": 21162,
+  "孭": 21163,
+  "屙": 21164,
+  "廸": 21165,
+  "彊": 21166,
+  "戇": 21167,
+  "戥": 21168,
+  "扚": 21169,
+  "扠": 21170,
+  "扺": 21171,
+  "扻": 21172,
+  "抆": 21173,
+  "抌": 21174,
+  "抺": 21175,
+  "捽": 21176,
+  "掕": 21177,
+  "掟": 21178,
+  "掹": 21179,
+  "揦": 21180,
+  "揼": 21181,
+  "揾": 21182,
+  "搣": 21183,
+  "搥": 21184,
+  "搲": 21185,
+  "摙": 21186,
+  "摷": 21187,
+  "撘": 21188,
+  "撳": 21189,
+  "攋": 21190,
+  "攰": 21191,
+  "曱": 21192,
+  "栢": 21193,
+  "梘": 21194,
+  "櫈": 21195,
+  "欅": 21196,
+  "殻": 21197,
+  "炆": 21198,
+  "烚": 21199,
+  "燶": 21200,
+  "猁": 21201,
+  "猢": 21202,
+  "獌": 21203,
+  "甴": 21204,
+  "痾": 21205,
+  "瘜": 21206,
+  "癈": 21207,
+  "癪": 21208,
+  "砵": 21209,
+  "祼": 21210,
+  "罅": 21211,
+  "罉": 21212,
+  "脷": 21213,
+  "蚑": 21214,
+  "蝻": 21215,
+  "袓": 21216,
+  "裇": 21217,
+  "褸": 21218,
+  "趷": 21219,
+  "跣": 21220,
+  "踎": 21221,
+  "踭": 21222,
+  "踼": 21223,
+  "躝": 21224,
+  "軚": 21225,
+  "鋭": 21226,
+  "錡": 21227,
+  "鍠": 21228,
+  "鎅": 21229,
+  "鏝": 21230,
+  "閂": 21231,
+  "閪": 21232,
+  "餸": 21233,
+  "騮": 21234,
+  "骹": 21235,
+  "髀": 21236,
+  "鰂": 21237,
+  "麖": 21238,
+  "黐": 21239,
+  "𠝹": 21240,
+  "𠵱": 21241,
+  "𠹌": 21242,
+  "𠺌": 21243,
+  "𠺘": 21244,
+  "𠻹": 21245,
+  "𠿪": 21246,
+  "𡃁": 21247,
+  "𢃇": 21248,
+  "𥄫": 21249,
+  "𨋢": 21250,
+  "𨳒": 21251,
+  "𪘲": 21252
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,14 @@

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

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff