Hugging Face's logo

cstr
/
phi-3-orpo-v8_16

Text Generation
Transformers
PyTorch
English
German
llama
text-generation-inference
unsloth
trl
orpo
conversational
Inference Endpoints
Model card Files Community
cstr commited on
Commit
7b197ed
•
1 Parent(s): 3cc957f

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +40 -0
  2. special_tokens_map.json +33 -0
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +351 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|end|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": true,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,351 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|step|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|function_output|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|tag|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|function_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|raw|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|continue|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|function_list|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": true,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|calc|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": true,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|code|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": true,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|/code|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": true,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|summary|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": true,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|resource|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": true,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|assistant_mask|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": true,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|start|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": true,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|message|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": true,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|fim_prefix|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": true,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|fim_middle|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": true,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|fim_suffix|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": true,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|meta_start|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": true,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|ipynb_marker|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": true,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|diff_marker|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": true,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|ghissue|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": true,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|ghreview|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": true,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|disc_start|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": true,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|disc_sep|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": true,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|disc_thread|><|query|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": true,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|/query|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": true,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|data|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": true,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|/data|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": true,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|sys|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": true,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|/sys|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": true,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|inst|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": true,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|/inst|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": true,
331
+ "single_word": false,
332
+ "special": true
333
+ }
334
+ },
335
+ "additional_special_tokens": [
336
+ "<|/inst|>"
337
+ ],
338
+ "bos_token": "<s>",
339
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{{ '<|system|>' + messages[0]['content'] + '<|end|>\n' }}{% set loop_messages = messages[1:] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + '<|end|>\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>' + message['content'] + '<|end|>\n' }}{% else %}{{ raise_exception('Only system, user, and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}",
340
+ "clean_up_tokenization_spaces": false,
341
+ "eos_token": "<|end|>",
342
+ "legacy": false,
343
+ "model_max_length": 4096,
344
+ "pad_token": "<|endoftext|>",
345
+ "padding_side": "left",
346
+ "sp_model_kwargs": {},
347
+ "spaces_between_special_tokens": false,
348
+ "tokenizer_class": "LlamaTokenizer",
349
+ "unk_token": "<unk>",
350
+ "use_default_system_prompt": false
351
+ }