keonhee commited on
Commit
d4d5699
·
verified ·
1 Parent(s): e86091f

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 49158,
3
+ "<|end_of_role|>": 49153,
4
+ "<|endoftext|>": 49159,
5
+ "<|start_of_role|>": 49152,
6
+ "<|strat_of_role|>": 49155,
7
+ "<|system|>": 49156,
8
+ "<|tool_call|>": 49154,
9
+ "<|user|>": 49157
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|strat_of_role|>",
4
+ "<|end_of_role|>",
5
+ "<|tool_call|>",
6
+ "<|system|>",
7
+ "<|user|>",
8
+ "<|assistant|>",
9
+ "<|endoftext|>"
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|end_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|end_of_text|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|end_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<filename>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<gh_stars>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<issue_start>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<issue_comment>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<issue_closed>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<jupyter_start>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<jupyter_text>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<jupyter_code>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<jupyter_output>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<empty_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<commit_before>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<commit_msg>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<commit_after>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<reponame>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "49152": {
158
+ "content": "<|start_of_role|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "49153": {
166
+ "content": "<|end_of_role|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "49154": {
174
+ "content": "<|tool_call|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "49155": {
182
+ "content": "<|strat_of_role|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "49156": {
190
+ "content": "<|system|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "49157": {
198
+ "content": "<|user|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "49158": {
206
+ "content": "<|assistant|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "49159": {
214
+ "content": "<|endoftext|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|strat_of_role|>",
224
+ "<|end_of_role|>",
225
+ "<|tool_call|>",
226
+ "<|system|>",
227
+ "<|user|>",
228
+ "<|assistant|>",
229
+ "<|endoftext|>"
230
+ ],
231
+ "bos_token": "<|end_of_text|>",
232
+ "chat_template": "{%- if tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>\n' }}\n {%- for tool in tools %}\n {{- tool | tojson(indent=4) }}\n {%- if not loop.last %}\n {{- '\n\n' }}\n {%- endif %}\n {%- endfor %}\n {{- '<|end_of_text|>\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n {{- '<|start_of_role|>system<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'user' %}\n {{- '<|start_of_role|>user<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant' %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- elif message['role'] == 'tool_response' %}\n {{- '<|start_of_role|>tool_response<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}",
233
+ "clean_up_tokenization_spaces": true,
234
+ "eos_token": "<|end_of_text|>",
235
+ "errors": "replace",
236
+ "max_length": 250,
237
+ "model_max_length": 9223372036854775807,
238
+ "pad_token": "<|end_of_text|>",
239
+ "padding_side": "left",
240
+ "stride": 0,
241
+ "tokenizer_class": "GPT2Tokenizer",
242
+ "truncation_side": "right",
243
+ "truncation_strategy": "longest_first",
244
+ "unk_token": "<|end_of_text|>",
245
+ "vocab_size": 49152
246
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff