Commit
•
cc66167
1
Parent(s):
3e343ed
Upload tokenizer
Browse files- added_tokens.json +102 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"㔷": 51344,
|
| 3 |
+
"㕷": 51299,
|
| 4 |
+
"㕸": 51304,
|
| 5 |
+
"㖭": 51275,
|
| 6 |
+
"㗅": 51297,
|
| 7 |
+
"㗩": 51281,
|
| 8 |
+
"㗳": 51283,
|
| 9 |
+
"㙮": 51293,
|
| 10 |
+
"㚵": 51354,
|
| 11 |
+
"㝫": 51289,
|
| 12 |
+
"㞋": 51335,
|
| 13 |
+
"㡌": 51316,
|
| 14 |
+
"㢌": 51315,
|
| 15 |
+
"㧗": 51328,
|
| 16 |
+
"㧜": 51329,
|
| 17 |
+
"㧬": 51317,
|
| 18 |
+
"㧵": 51338,
|
| 19 |
+
"㨂": 51272,
|
| 20 |
+
"㨢": 51320,
|
| 21 |
+
"㨾": 51346,
|
| 22 |
+
"㩜": 51287,
|
| 23 |
+
"㪣": 51323,
|
| 24 |
+
"㬢": 51295,
|
| 25 |
+
"㭍": 51277,
|
| 26 |
+
"㯲": 51324,
|
| 27 |
+
"㴝": 51278,
|
| 28 |
+
"㺀": 51300,
|
| 29 |
+
"䀆": 51306,
|
| 30 |
+
"䁠": 51327,
|
| 31 |
+
"䄛": 51290,
|
| 32 |
+
"䇔": 51347,
|
| 33 |
+
"䊨": 51352,
|
| 34 |
+
"䎵": 51314,
|
| 35 |
+
"䐉": 51353,
|
| 36 |
+
"䑛": 51302,
|
| 37 |
+
"䜔": 51343,
|
| 38 |
+
"䝱": 51359,
|
| 39 |
+
"䡱": 51339,
|
| 40 |
+
"䳆": 51309,
|
| 41 |
+
"嘺": 51325,
|
| 42 |
+
"朼": 51342,
|
| 43 |
+
"簂": 51366,
|
| 44 |
+
"贂": 51345,
|
| 45 |
+
"龧": 51348,
|
| 46 |
+
"龬": 51334,
|
| 47 |
+
"鿋": 51358,
|
| 48 |
+
"𠄘": 51282,
|
| 49 |
+
"𠱁": 51279,
|
| 50 |
+
"𠲖": 51296,
|
| 51 |
+
"𠳔": 51298,
|
| 52 |
+
"𠴱": 51273,
|
| 53 |
+
"𠵿": 51303,
|
| 54 |
+
"𠸄": 51364,
|
| 55 |
+
"𠹳": 51370,
|
| 56 |
+
"𠹺": 51340,
|
| 57 |
+
"𠼮": 51363,
|
| 58 |
+
"𠼱": 51349,
|
| 59 |
+
"𠾐": 51367,
|
| 60 |
+
"𡁵": 51280,
|
| 61 |
+
"𡃓": 51308,
|
| 62 |
+
"𡃤": 51362,
|
| 63 |
+
"𡒊": 51369,
|
| 64 |
+
"𡥼": 51351,
|
| 65 |
+
"𢇁": 51332,
|
| 66 |
+
"𢇃": 51341,
|
| 67 |
+
"𢓭": 51360,
|
| 68 |
+
"𢡱": 51319,
|
| 69 |
+
"𢤦": 51355,
|
| 70 |
+
"𢦀": 51305,
|
| 71 |
+
"𢦓": 51330,
|
| 72 |
+
"𢫏": 51312,
|
| 73 |
+
"𢭃": 51276,
|
| 74 |
+
"𢯎": 51291,
|
| 75 |
+
"𢱑": 51285,
|
| 76 |
+
"𢱕": 51294,
|
| 77 |
+
"𢲡": 51288,
|
| 78 |
+
"𢲷": 51368,
|
| 79 |
+
"𢴇": 51301,
|
| 80 |
+
"𢵧": 51356,
|
| 81 |
+
"𣲙": 51336,
|
| 82 |
+
"𣺉": 51361,
|
| 83 |
+
"𣾀": 51310,
|
| 84 |
+
"𣿬": 51333,
|
| 85 |
+
"𤗲": 51284,
|
| 86 |
+
"𤘅": 51292,
|
| 87 |
+
"𤶸": 51350,
|
| 88 |
+
"𥄫": 51271,
|
| 89 |
+
"𥖁": 51311,
|
| 90 |
+
"𥱊": 51274,
|
| 91 |
+
"𦟌": 51307,
|
| 92 |
+
"𦣇": 51357,
|
| 93 |
+
"𧄌": 51318,
|
| 94 |
+
"𧇣": 51365,
|
| 95 |
+
"𨂽": 51322,
|
| 96 |
+
"𨂾": 51286,
|
| 97 |
+
"𨈇": 51313,
|
| 98 |
+
"𨌺": 51337,
|
| 99 |
+
"𨤳": 51326,
|
| 100 |
+
"𩓙": 51321,
|
| 101 |
+
"𪂹": 51331
|
| 102 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[EOS]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_basic_tokenize": true,
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[EOS]",
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"never_split": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"sep_token": "[SEP]",
|
| 13 |
+
"strip_accents": null,
|
| 14 |
+
"tokenize_chinese_chars": true,
|
| 15 |
+
"tokenizer_class": "BertTokenizer",
|
| 16 |
+
"unk_token": "[UNK]"
|
| 17 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|