Hugging Face's logo

zaydzuhri
/
tasklets_tokenizer_50

Model card Files
xet
Community
zaydzuhri commited on
Commit
6448101
·
verified ·
1 Parent(s): 2fab2ea

Add tokenizer files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +161 -0
  3. tokenizer_config.json +53 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "eos_token": "[EOS]",
4
+ "mask_token": "_",
5
+ "pad_token": "[PAD]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "_",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[UNK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[BOS]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[EOS]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "Sequence",
54
+ "normalizers": [
55
+ {
56
+ "type": "NFD"
57
+ },
58
+ {
59
+ "type": "StripAccents"
60
+ },
61
+ {
62
+ "type": "Lowercase"
63
+ }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Whitespace"
68
+ },
69
+ "post_processor": null,
70
+ "decoder": null,
71
+ "model": {
72
+ "type": "WordLevel",
73
+ "vocab": {
74
+ "_": 0,
75
+ "[PAD]": 1,
76
+ "[UNK]": 2,
77
+ "[BOS]": 3,
78
+ "[EOS]": 4,
79
+ "a": 5,
80
+ "b": 6,
81
+ "c": 7,
82
+ "d": 8,
83
+ "e": 9,
84
+ "f": 10,
85
+ "g": 11,
86
+ "h": 12,
87
+ "i": 13,
88
+ "j": 14,
89
+ "k": 15,
90
+ "l": 16,
91
+ "m": 17,
92
+ "n": 18,
93
+ "o": 19,
94
+ "p": 20,
95
+ "q": 21,
96
+ "r": 22,
97
+ "s": 23,
98
+ "t": 24,
99
+ "u": 25,
100
+ "v": 26,
101
+ "w": 27,
102
+ "x": 28,
103
+ "y": 29,
104
+ "z": 30,
105
+ "0": 31,
106
+ "1": 32,
107
+ "2": 33,
108
+ "3": 34,
109
+ "4": 35,
110
+ "5": 36,
111
+ "6": 37,
112
+ "7": 38,
113
+ "8": 39,
114
+ "9": 40,
115
+ "10": 41,
116
+ "11": 42,
117
+ "12": 43,
118
+ "13": 44,
119
+ "14": 45,
120
+ "15": 46,
121
+ "16": 47,
122
+ "17": 48,
123
+ "18": 49,
124
+ "19": 50,
125
+ "20": 51,
126
+ "21": 52,
127
+ "22": 53,
128
+ "23": 54,
129
+ "24": 55,
130
+ "25": 56,
131
+ "26": 57,
132
+ "27": 58,
133
+ "28": 59,
134
+ "29": 60,
135
+ "30": 61,
136
+ "31": 62,
137
+ "32": 63,
138
+ "33": 64,
139
+ "34": 65,
140
+ "35": 66,
141
+ "36": 67,
142
+ "37": 68,
143
+ "38": 69,
144
+ "39": 70,
145
+ "40": 71,
146
+ "41": 72,
147
+ "42": 73,
148
+ "43": 74,
149
+ "44": 75,
150
+ "45": 76,
151
+ "46": 77,
152
+ "47": 78,
153
+ "48": 79,
154
+ "49": 80,
155
+ "50": 81,
156
+ "|": 82,
157
+ "?": 83
158
+ },
159
+ "unk_token": "[UNK]"
160
+ }
161
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "_",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[BOS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[EOS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[BOS]",
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "[EOS]",
47
+ "extra_special_tokens": {},
48
+ "mask_token": "_",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "pad_token": "[PAD]",
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "unk_token": "[UNK]"
53
+ }