luke-kr commited on
Commit
da3ae91
·
verified ·
1 Parent(s): a97a22a

Upload tokenizer

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools is iterable and tools | length > 0 %}
2
+ {{- '<|im_start|><|system|>'}}
3
+ {{- '당신은 도구 호출 기능을 갖춘 유용한 도우미입니다. 사용자의 요청을 처리하기 위해서 필요한 도구가 주어진 목록에 있는 경우 도구 호출로 응답하세요.
4
+ 필요한 도구가 목록에 없는 경우에는 도구 호출 없이 사용자가 요구한 정보를 제공하세요.
5
+ 필요한 도구가 목록에 있지만 해당 도구를 호출하는데 필요한 argument 정보가 부족한 경우 해당 정보를 사용자에게 요청하세요.
6
+ 사용자의 요청을 처리하기 위해 여러번 도구를 호출할 수 있어야 합니다.
7
+ 도구 호출 이후 도구 실행 결과를 입력으로 받으면 해당 결과를 활용하여 답변을 생성하세요.
8
+
9
+ 다음은 접근할 수 있는 도구들의 목록 입니다:
10
+ <tools>
11
+ '}}
12
+ {%- for t in tools %}
13
+ {{- t | tojson }}
14
+ {{- '
15
+ ' }}
16
+ {%- endfor %}
17
+ {{- '</tools>' }}
18
+ {{- '
19
+
20
+ 도구를 호출하려면 아래의 JSON으로 응답하세요.
21
+ 도구 호출 형식: <tool_call>{"name": 도구 이름, "arguments": dictionary 형태의 도구 인자값}</tool_call>' }}
22
+ {{- '<|im_end|>' }}
23
+ {%- endif %}
24
+
25
+ {%- for message in messages %}
26
+ {%- if message.role == 'system' %}
27
+ {{- '<|im_start|><|system|>' + message.content + '<|im_end|>'}}
28
+ {%- elif message.role == 'user' %}
29
+ {{- '<|im_start|><|user|>' + message.content + '<|im_end|>'}}
30
+ {%- elif message.role == 'assistant' %}
31
+ {{- '<|im_start|><|assistant|>'}}
32
+ {%- set content = '' %}
33
+ {%- if message.content is defined %}
34
+ {%- set content = message.content %}
35
+ {%- endif %}
36
+
37
+ {%- if add_generation_prompt and not (message.reasoning_content is defined and message.reasoning_content is not none) %}
38
+ {%- if '</think>' in message.content %}
39
+ {%- set content = message.content.split('</think>'.strip())[-1].lstrip('\n') %}
40
+ {%- endif %}
41
+ {%- endif %}
42
+
43
+ {{- content}}
44
+ {%- if message.tool_calls is defined %}
45
+ {%- for tool_call in message.tool_calls %}
46
+ {%- if tool_call.function is defined %}
47
+ {%- set tool_call = tool_call.function %}
48
+ {%- endif %}
49
+ {{- '<tool_call>' }}
50
+ {{- '{' }}
51
+ {{- '"name": "' }}
52
+ {{- tool_call.name }}
53
+ {{- '"' }}
54
+ {%- if tool_call.arguments is defined %}
55
+ {{- ', ' }}
56
+ {{- '"arguments": ' }}
57
+ {{- tool_call.arguments|tojson }}
58
+ {%- endif %}
59
+ {{- '}' }}
60
+ {{- '</tool_call>' }}
61
+ {%- endfor %}
62
+ {%- endif %}
63
+ {{- '<|im_end|>'}}
64
+
65
+ {%- elif message.role == 'tool' %}
66
+ {{- '<|im_start|><|extra_id_13|><tool_output>' + message.content + '</tool_output><|im_end|>'}}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+
70
+ {%- if add_generation_prompt %}
71
+ {{- '<|im_start|><|assistant|>' }}
72
+ {%- endif %}
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|pad|>",
5
+ "<|unk|>",
6
+ "<|sep|>",
7
+ "<|mask|>",
8
+ "<|cls|>",
9
+ "<|image|>",
10
+ "<|audio|>",
11
+ "<|user|>",
12
+ "<|system|>",
13
+ "<|assistant|>",
14
+ "<|extra_id_0|>",
15
+ "<|extra_id_1|>",
16
+ "<|extra_id_2|>",
17
+ "<|extra_id_3|>",
18
+ "<|extra_id_4|>",
19
+ "<|extra_id_5|>",
20
+ "<|extra_id_6|>",
21
+ "<|extra_id_7|>",
22
+ "<|extra_id_8|>",
23
+ "<|extra_id_9|>",
24
+ "<|extra_id_10|>",
25
+ "<|extra_id_13|>",
26
+ "<|im_start|>",
27
+ "<|im_sep|>",
28
+ "<|im_end|>",
29
+ "<|resident_reg|>",
30
+ "<|foreigner_reg|>",
31
+ "<|business_reg|>",
32
+ "<|credit_card|>",
33
+ "<|passport|>",
34
+ "<|driver_license|>",
35
+ "<|telephone|>",
36
+ "<|health_insurance|>",
37
+ "<|bank_account|>"
38
+ ],
39
+ "bos_token": {
40
+ "content": "<|endoftext|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "cls_token": {
47
+ "content": "<|cls|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "eos_token": {
54
+ "content": "<|im_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "mask_token": {
61
+ "content": "<|mask|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "pad_token": "<|im_end|>",
68
+ "sep_token": {
69
+ "content": "<|sep|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ },
75
+ "unk_token": {
76
+ "content": "<|unk|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ }
82
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,385 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|pad|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|unk|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|sep|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|mask|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|cls|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|image|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|audio|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|user|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|assistant|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|extra_id_0|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|extra_id_1|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|extra_id_2|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<|extra_id_3|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<|extra_id_4|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<|extra_id_5|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<|extra_id_6|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<|extra_id_7|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "19": {
158
+ "content": "<|extra_id_8|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "20": {
166
+ "content": "<|extra_id_9|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "21": {
174
+ "content": "<|extra_id_10|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "22": {
182
+ "content": "</think>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<think>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<|extra_id_13|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "25": {
206
+ "content": "<|im_start|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "26": {
214
+ "content": "<|im_sep|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "27": {
222
+ "content": "<|im_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "28": {
230
+ "content": "<|resident_reg|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "29": {
238
+ "content": "<|foreigner_reg|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "30": {
246
+ "content": "<|business_reg|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "31": {
254
+ "content": "<|credit_card|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32": {
262
+ "content": "<|passport|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "33": {
270
+ "content": "<|driver_license|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "34": {
278
+ "content": "<|telephone|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "35": {
286
+ "content": "<|health_insurance|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "36": {
294
+ "content": "<|bank_account|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "37": {
302
+ "content": "</tool_output>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<tool_output>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "</tool_call>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<tool_call>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ }
333
+ },
334
+ "additional_special_tokens": [
335
+ "<|endoftext|>",
336
+ "<|pad|>",
337
+ "<|unk|>",
338
+ "<|sep|>",
339
+ "<|mask|>",
340
+ "<|cls|>",
341
+ "<|image|>",
342
+ "<|audio|>",
343
+ "<|user|>",
344
+ "<|system|>",
345
+ "<|assistant|>",
346
+ "<|extra_id_0|>",
347
+ "<|extra_id_1|>",
348
+ "<|extra_id_2|>",
349
+ "<|extra_id_3|>",
350
+ "<|extra_id_4|>",
351
+ "<|extra_id_5|>",
352
+ "<|extra_id_6|>",
353
+ "<|extra_id_7|>",
354
+ "<|extra_id_8|>",
355
+ "<|extra_id_9|>",
356
+ "<|extra_id_10|>",
357
+ "<|extra_id_13|>",
358
+ "<|im_start|>",
359
+ "<|im_sep|>",
360
+ "<|im_end|>",
361
+ "<|resident_reg|>",
362
+ "<|foreigner_reg|>",
363
+ "<|business_reg|>",
364
+ "<|credit_card|>",
365
+ "<|passport|>",
366
+ "<|driver_license|>",
367
+ "<|telephone|>",
368
+ "<|health_insurance|>",
369
+ "<|bank_account|>"
370
+ ],
371
+ "bos_token": "<|endoftext|>",
372
+ "clean_up_tokenization_spaces": true,
373
+ "cls_token": "<|cls|>",
374
+ "eod_token": "<|endoftext|>",
375
+ "eos_token": "<|im_end|>",
376
+ "errors": "replace",
377
+ "extra_special_tokens": {},
378
+ "mask_token": "<|mask|>",
379
+ "model_max_length": 16384,
380
+ "pad_token": "<|im_end|>",
381
+ "sep_token": "<|sep|>",
382
+ "tokenizer_class": "GPT2Tokenizer",
383
+ "unk_token": "<|unk|>",
384
+ "vocab_size": 102400
385
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff