Hugging Face's logo

RaymondLi
/
gpt-4-tokenizer-sc-tokens

Model card Files Community
RaymondLi commited on
Commit
90cd208
•
1 Parent(s): b3ebc06

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +25 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +26 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +216 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<commit_after>": 100279,
3
+ "<commit_before>": 100292,
4
+ "<commit_msg>": 100286,
5
+ "<empty_output>": 100293,
6
+ "<filename>": 100283,
7
+ "<fim_middle>": 100281,
8
+ "<fim_pad>": 100287,
9
+ "<fim_prefix>": 100285,
10
+ "<fim_suffix>": 100284,
11
+ "<gh_stars>": 100277,
12
+ "<issue_closed>": 100291,
13
+ "<issue_comment>": 100288,
14
+ "<issue_start>": 100278,
15
+ "<jupyter_code>": 100282,
16
+ "<jupyter_output>": 100294,
17
+ "<jupyter_start>": 100290,
18
+ "<jupyter_text>": 100280,
19
+ "<reponame>": 100289,
20
+ "<|endofprompt|>": 100276,
21
+ "<|endoftext|>": 100257,
22
+ "<|fim_middle|>": 100259,
23
+ "<|fim_prefix|>": 100258,
24
+ "<|fim_suffix|>": 100260
25
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<gh_stars>",
4
+ "<issue_start>",
5
+ "<commit_after>",
6
+ "<jupyter_text>",
7
+ "<fim_middle>",
8
+ "<|endoftext|>",
9
+ "<jupyter_code>",
10
+ "<filename>",
11
+ "<fim_suffix>",
12
+ "<fim_prefix>",
13
+ "<commit_msg>",
14
+ "<fim_pad>",
15
+ "<issue_comment>",
16
+ "<reponame>",
17
+ "<jupyter_start>",
18
+ "<issue_closed>",
19
+ "<commit_before>",
20
+ "<empty_output>",
21
+ "<jupyter_output>"
22
+ ],
23
+ "bos_token": "<|endoftext|>",
24
+ "eos_token": "<|endoftext|>",
25
+ "unk_token": "<|endoftext|>"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "100257": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100258": {
13
+ "content": "<|fim_prefix|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100259": {
21
+ "content": "<|fim_middle|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100260": {
29
+ "content": "<|fim_suffix|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100276": {
37
+ "content": "<|endofprompt|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100277": {
45
+ "content": "<gh_stars>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100278": {
53
+ "content": "<issue_start>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100279": {
61
+ "content": "<commit_after>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100280": {
69
+ "content": "<jupyter_text>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100281": {
77
+ "content": "<fim_middle>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100282": {
85
+ "content": "<jupyter_code>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100283": {
93
+ "content": "<filename>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100284": {
101
+ "content": "<fim_suffix>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100285": {
109
+ "content": "<fim_prefix>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100286": {
117
+ "content": "<commit_msg>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100287": {
125
+ "content": "<fim_pad>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100288": {
133
+ "content": "<issue_comment>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100289": {
141
+ "content": "<reponame>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100290": {
149
+ "content": "<jupyter_start>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100291": {
157
+ "content": "<issue_closed>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "100292": {
165
+ "content": "<commit_before>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "100293": {
173
+ "content": "<empty_output>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "100294": {
181
+ "content": "<jupyter_output>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<gh_stars>",
191
+ "<issue_start>",
192
+ "<commit_after>",
193
+ "<jupyter_text>",
194
+ "<fim_middle>",
195
+ "<|endoftext|>",
196
+ "<jupyter_code>",
197
+ "<filename>",
198
+ "<fim_suffix>",
199
+ "<fim_prefix>",
200
+ "<commit_msg>",
201
+ "<fim_pad>",
202
+ "<issue_comment>",
203
+ "<reponame>",
204
+ "<jupyter_start>",
205
+ "<issue_closed>",
206
+ "<commit_before>",
207
+ "<empty_output>",
208
+ "<jupyter_output>"
209
+ ],
210
+ "bos_token": "<|endoftext|>",
211
+ "clean_up_tokenization_spaces": false,
212
+ "eos_token": "<|endoftext|>",
213
+ "model_max_length": 8192,
214
+ "tokenizer_class": "GPT2Tokenizer",
215
+ "unk_token": "<|endoftext|>"
216
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff