Hugging Face's logo

Owaner
/
CodexTokenizer6k

Transformers
Model card Files
xet
Community
Owaner commited on
Commit
2b2fd35
·
verified ·
1 Parent(s): a45bf2a

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +10 -1
  2. tokenizer.json +99 -0
  3. tokenizer_config.json +90 -0
special_tokens_map.json CHANGED
@@ -1 +1,10 @@
1
- {}
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "[EOS]",
3
+ "pad_token": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ }
tokenizer.json CHANGED
@@ -47,6 +47,105 @@
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  }
51
  ],
52
  "normalizer": {
 
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
50
+ },
51
+ {
52
+ "id": 6000,
53
+ "content": "[EOS]",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 6001,
62
+ "content": " ",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": false
68
+ },
69
+ {
70
+ "id": 6002,
71
+ "content": " ",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 6003,
80
+ "content": " ",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 6004,
89
+ "content": " ",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 6005,
98
+ "content": " ",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 6006,
107
+ "content": " ",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 6007,
116
+ "content": " ",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 6008,
125
+ "content": " ",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 6009,
134
+ "content": " ",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 6010,
143
+ "content": " ",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
  }
150
  ],
151
  "normalizer": {
tokenizer_config.json CHANGED
@@ -39,9 +39,99 @@
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
  "clean_up_tokenization_spaces": true,
 
45
  "model_max_length": 1000000000000000019884624838656,
 
46
  "tokenizer_class": "PreTrainedTokenizerFast"
47
  }
 
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "6000": {
44
+ "content": "[EOS]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6001": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "6002": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "6003": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "6004": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "6005": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "6006": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "6007": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "6008": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "6009": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "6010": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
  }
131
  },
132
  "clean_up_tokenization_spaces": true,
133
+ "eos_token": "[EOS]",
134
  "model_max_length": 1000000000000000019884624838656,
135
+ "pad_token": "[PAD]",
136
  "tokenizer_class": "PreTrainedTokenizerFast"
137
  }