Hugging Face's logo

Vikhrmodels
/
Vikhr-7B-instruct_0.3

Text Generation
Transformers
Safetensors
llama
trl
sft
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
2
AlexWortega commited on
Commit
06f2203
•
1 Parent(s): ae344d3

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +37 -0
  2. special_tokens_map.json +40 -0
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +327 -0
added_tokens.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|future_token_32|>": 60223,
3
+ "<|future_token_33|>": 60224,
4
+ "<|future_token_34|>": 60225,
5
+ "<|future_token_35|>": 60226,
6
+ "<|future_token_36|>": 60227,
7
+ "<|future_token_37|>": 60228,
8
+ "<|future_token_38|>": 60229,
9
+ "<|future_token_39|>": 60230,
10
+ "<|future_token_40|>": 60231,
11
+ "<|future_token_41|>": 60232,
12
+ "<|future_token_42|>": 60233,
13
+ "<|future_token_43|>": 60234,
14
+ "<|future_token_44|>": 60235,
15
+ "<|future_token_45|>": 60236,
16
+ "<|future_token_46|>": 60237,
17
+ "<|future_token_47|>": 60238,
18
+ "<|future_token_48|>": 60239,
19
+ "<|future_token_49|>": 60240,
20
+ "<|future_token_50|>": 60241,
21
+ "<|future_token_51|>": 60242,
22
+ "<|future_token_52|>": 60243,
23
+ "<|future_token_53|>": 60244,
24
+ "<|future_token_54|>": 60245,
25
+ "<|future_token_55|>": 60246,
26
+ "<|future_token_56|>": 60247,
27
+ "<|future_token_57|>": 60248,
28
+ "<|future_token_58|>": 60249,
29
+ "<|future_token_59|>": 60250,
30
+ "<|future_token_60|>": 60251,
31
+ "<|future_token_61|>": 60252,
32
+ "<|future_token_62|>": 60253,
33
+ "<|future_token_63|>": 60254,
34
+ "<|future_token_64|>": 60255,
35
+ "<|im_end|>": 60257,
36
+ "<|im_start|>": 60256
37
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "</s>",
33
+ "unk_token": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a318b32e8f3563332901fb4a798d4718a1501e9a78b032f72002685bc9b9a9
3
+ size 1105908
tokenizer_config.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "60223": {
31
+ "content": "<|future_token_32|>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "60224": {
39
+ "content": "<|future_token_33|>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "60225": {
47
+ "content": "<|future_token_34|>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "60226": {
55
+ "content": "<|future_token_35|>",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "60227": {
63
+ "content": "<|future_token_36|>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "60228": {
71
+ "content": "<|future_token_37|>",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "60229": {
79
+ "content": "<|future_token_38|>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "60230": {
87
+ "content": "<|future_token_39|>",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "60231": {
95
+ "content": "<|future_token_40|>",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "60232": {
103
+ "content": "<|future_token_41|>",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "60233": {
111
+ "content": "<|future_token_42|>",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "60234": {
119
+ "content": "<|future_token_43|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "60235": {
127
+ "content": "<|future_token_44|>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "60236": {
135
+ "content": "<|future_token_45|>",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "60237": {
143
+ "content": "<|future_token_46|>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "60238": {
151
+ "content": "<|future_token_47|>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "60239": {
159
+ "content": "<|future_token_48|>",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "60240": {
167
+ "content": "<|future_token_49|>",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "60241": {
175
+ "content": "<|future_token_50|>",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "60242": {
183
+ "content": "<|future_token_51|>",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "60243": {
191
+ "content": "<|future_token_52|>",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "60244": {
199
+ "content": "<|future_token_53|>",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "60245": {
207
+ "content": "<|future_token_54|>",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "60246": {
215
+ "content": "<|future_token_55|>",
216
+ "lstrip": false,
217
+ "normalized": true,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "60247": {
223
+ "content": "<|future_token_56|>",
224
+ "lstrip": false,
225
+ "normalized": true,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "60248": {
231
+ "content": "<|future_token_57|>",
232
+ "lstrip": false,
233
+ "normalized": true,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "60249": {
239
+ "content": "<|future_token_58|>",
240
+ "lstrip": false,
241
+ "normalized": true,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": false
245
+ },
246
+ "60250": {
247
+ "content": "<|future_token_59|>",
248
+ "lstrip": false,
249
+ "normalized": true,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": false
253
+ },
254
+ "60251": {
255
+ "content": "<|future_token_60|>",
256
+ "lstrip": false,
257
+ "normalized": true,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "60252": {
263
+ "content": "<|future_token_61|>",
264
+ "lstrip": false,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "60253": {
271
+ "content": "<|future_token_62|>",
272
+ "lstrip": false,
273
+ "normalized": true,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "60254": {
279
+ "content": "<|future_token_63|>",
280
+ "lstrip": false,
281
+ "normalized": true,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "60255": {
287
+ "content": "<|future_token_64|>",
288
+ "lstrip": false,
289
+ "normalized": true,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "60256": {
295
+ "content": "<|im_start|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "60257": {
303
+ "content": "<|im_end|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ }
310
+ },
311
+ "additional_special_tokens": [
312
+ "<|im_start|>",
313
+ "<|im_end|>"
314
+ ],
315
+ "bos_token": "<s>",
316
+ "chat_template": "<s>{% 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 %}",
317
+ "clean_up_tokenization_spaces": false,
318
+ "eos_token": "</s>",
319
+ "legacy": true,
320
+ "model_max_length": 1512,
321
+ "pad_token": "</s>",
322
+ "sp_model_kwargs": {},
323
+ "spaces_between_special_tokens": false,
324
+ "tokenizer_class": "LlamaTokenizer",
325
+ "unk_token": "<unk>",
326
+ "use_default_system_prompt": true
327
+ }