Hugging Face's logo

DWDMaiMai
/
tiktoken_cl100k_base

Transformers
tokenizers
Inference Endpoints
Model card Files Community
DWDMaiMai commited on
Commit
fe9a84b
•
1 Parent(s): b3a472b

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +23 -0
  2. tokenizer.json +160 -0
  3. tokenizer_config.json +151 -0
  4. vocab.json +0 -0
special_tokens_map.json CHANGED
@@ -1,4 +1,27 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
  "unk_token": "<|endoftext|>"
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|fim_prefix|>",
5
+ "<|fim_middle|>",
6
+ "<|fim_suffix|>",
7
+ "<|endofprompt|>",
8
+ "<|_unuse_missing_100256|>",
9
+ "<|_unuse_missing_100261|>",
10
+ "<|_unuse_missing_100262|>",
11
+ "<|_unuse_missing_100263|>",
12
+ "<|_unuse_missing_100264|>",
13
+ "<|_unuse_missing_100265|>",
14
+ "<|_unuse_missing_100266|>",
15
+ "<|_unuse_missing_100267|>",
16
+ "<|_unuse_missing_100268|>",
17
+ "<|_unuse_missing_100269|>",
18
+ "<|_unuse_missing_100270|>",
19
+ "<|_unuse_missing_100271|>",
20
+ "<|_unuse_missing_100272|>",
21
+ "<|_unuse_missing_100273|>",
22
+ "<|_unuse_missing_100274|>",
23
+ "<|_unuse_missing_100275|>"
24
+ ],
25
  "bos_token": "<|endoftext|>",
26
  "eos_token": "<|endoftext|>",
27
  "unk_token": "<|endoftext|>"
tokenizer.json CHANGED
@@ -3,6 +3,15 @@
3
  "truncation": null,
4
  "padding": null,
5
  "added_tokens": [
 
 
 
 
 
 
 
 
 
6
  {
7
  "id": 100257,
8
  "content": "<|endoftext|>",
@@ -39,6 +48,141 @@
39
  "normalized": false,
40
  "special": true
41
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  {
43
  "id": 100276,
44
  "content": "<|endofprompt|>",
@@ -100346,10 +100490,26 @@
100346
  ".WaitFor": 100253,
100347
  "Ġdaycare": 100254,
100348
  "ĠConveyor": 100255,
 
100349
  "<|endoftext|>": 100257,
100350
  "<|fim_prefix|>": 100258,
100351
  "<|fim_middle|>": 100259,
100352
  "<|fim_suffix|>": 100260,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
100353
  "<|endofprompt|>": 100276
100354
  },
100355
  "merges": [
 
3
  "truncation": null,
4
  "padding": null,
5
  "added_tokens": [
6
+ {
7
+ "id": 100256,
8
+ "content": "<|_unuse_missing_100256|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
  {
16
  "id": 100257,
17
  "content": "<|endoftext|>",
 
48
  "normalized": false,
49
  "special": true
50
  },
51
+ {
52
+ "id": 100261,
53
+ "content": "<|_unuse_missing_100261|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 100262,
62
+ "content": "<|_unuse_missing_100262|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 100263,
71
+ "content": "<|_unuse_missing_100263|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 100264,
80
+ "content": "<|_unuse_missing_100264|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 100265,
89
+ "content": "<|_unuse_missing_100265|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 100266,
98
+ "content": "<|_unuse_missing_100266|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 100267,
107
+ "content": "<|_unuse_missing_100267|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 100268,
116
+ "content": "<|_unuse_missing_100268|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 100269,
125
+ "content": "<|_unuse_missing_100269|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 100270,
134
+ "content": "<|_unuse_missing_100270|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 100271,
143
+ "content": "<|_unuse_missing_100271|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 100272,
152
+ "content": "<|_unuse_missing_100272|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 100273,
161
+ "content": "<|_unuse_missing_100273|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 100274,
170
+ "content": "<|_unuse_missing_100274|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 100275,
179
+ "content": "<|_unuse_missing_100275|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
  {
187
  "id": 100276,
188
  "content": "<|endofprompt|>",
 
100490
  ".WaitFor": 100253,
100491
  "Ġdaycare": 100254,
100492
  "ĠConveyor": 100255,
100493
+ "<|_unuse_missing_100256|>": 100256,
100494
  "<|endoftext|>": 100257,
100495
  "<|fim_prefix|>": 100258,
100496
  "<|fim_middle|>": 100259,
100497
  "<|fim_suffix|>": 100260,
100498
+ "<|_unuse_missing_100261|>": 100261,
100499
+ "<|_unuse_missing_100262|>": 100262,
100500
+ "<|_unuse_missing_100263|>": 100263,
100501
+ "<|_unuse_missing_100264|>": 100264,
100502
+ "<|_unuse_missing_100265|>": 100265,
100503
+ "<|_unuse_missing_100266|>": 100266,
100504
+ "<|_unuse_missing_100267|>": 100267,
100505
+ "<|_unuse_missing_100268|>": 100268,
100506
+ "<|_unuse_missing_100269|>": 100269,
100507
+ "<|_unuse_missing_100270|>": 100270,
100508
+ "<|_unuse_missing_100271|>": 100271,
100509
+ "<|_unuse_missing_100272|>": 100272,
100510
+ "<|_unuse_missing_100273|>": 100273,
100511
+ "<|_unuse_missing_100274|>": 100274,
100512
+ "<|_unuse_missing_100275|>": 100275,
100513
  "<|endofprompt|>": 100276
100514
  },
100515
  "merges": [
tokenizer_config.json CHANGED
@@ -1,6 +1,14 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
4
  "100257": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
@@ -33,6 +41,126 @@
33
  "single_word": false,
34
  "special": true
35
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  "100276": {
37
  "content": "<|endofprompt|>",
38
  "lstrip": false,
@@ -42,6 +170,29 @@
42
  "special": true
43
  }
44
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "bos_token": "<|endoftext|>",
46
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
47
  "clean_up_tokenization_spaces": true,
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|_unuse_missing_100256|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
  "100257": {
13
  "content": "<|endoftext|>",
14
  "lstrip": false,
 
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "100261": {
45
+ "content": "<|_unuse_missing_100261|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|_unuse_missing_100262|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|_unuse_missing_100263|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|_unuse_missing_100264|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|_unuse_missing_100265|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|_unuse_missing_100266|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|_unuse_missing_100267|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|_unuse_missing_100268|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|_unuse_missing_100269|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<|_unuse_missing_100270|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "<|_unuse_missing_100271|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<|_unuse_missing_100272|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "<|_unuse_missing_100273|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<|_unuse_missing_100274|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "<|_unuse_missing_100275|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
  "100276": {
165
  "content": "<|endofprompt|>",
166
  "lstrip": false,
 
170
  "special": true
171
  }
172
  },
173
+ "additional_special_tokens": [
174
+ "<|endoftext|>",
175
+ "<|fim_prefix|>",
176
+ "<|fim_middle|>",
177
+ "<|fim_suffix|>",
178
+ "<|endofprompt|>",
179
+ "<|_unuse_missing_100256|>",
180
+ "<|_unuse_missing_100261|>",
181
+ "<|_unuse_missing_100262|>",
182
+ "<|_unuse_missing_100263|>",
183
+ "<|_unuse_missing_100264|>",
184
+ "<|_unuse_missing_100265|>",
185
+ "<|_unuse_missing_100266|>",
186
+ "<|_unuse_missing_100267|>",
187
+ "<|_unuse_missing_100268|>",
188
+ "<|_unuse_missing_100269|>",
189
+ "<|_unuse_missing_100270|>",
190
+ "<|_unuse_missing_100271|>",
191
+ "<|_unuse_missing_100272|>",
192
+ "<|_unuse_missing_100273|>",
193
+ "<|_unuse_missing_100274|>",
194
+ "<|_unuse_missing_100275|>"
195
+ ],
196
  "bos_token": "<|endoftext|>",
197
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
198
  "clean_up_tokenization_spaces": true,
vocab.json CHANGED
The diff for this file is too large to render. See raw diff