AIFunOver commited on
Commit
792d0d8
1 Parent(s): f98ebab

Upload openvino_tokenizer.xml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openvino_tokenizer.xml +433 -0
openvino_tokenizer.xml ADDED
@@ -0,0 +1,433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="string_input" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="string_input">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_951956" type="Const" version="opset1">
13
+ <data element_type="i32" shape="" offset="0" size="4" />
14
+ <output>
15
+ <port id="0" precision="I32" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="Constant_951948" type="Const" version="opset1">
19
+ <data element_type="u8" shape="1536689" offset="4" size="1536689" />
20
+ <output>
21
+ <port id="0" precision="U8">
22
+ <dim>1536689</dim>
23
+ </port>
24
+ </output>
25
+ </layer>
26
+ <layer id="3" name="Constant_951952" type="Const" version="opset1">
27
+ <data element_type="u8" shape="787" offset="1536693" size="787" />
28
+ <output>
29
+ <port id="0" precision="U8">
30
+ <dim>787</dim>
31
+ </port>
32
+ </output>
33
+ </layer>
34
+ <layer id="4" name="StringTensorUnpack_951953" type="StringTensorUnpack" version="extension">
35
+ <data mode="begins_ends" />
36
+ <input>
37
+ <port id="0" precision="U8">
38
+ <dim>787</dim>
39
+ </port>
40
+ </input>
41
+ <output>
42
+ <port id="1" precision="I32">
43
+ <dim>-1</dim>
44
+ </port>
45
+ <port id="2" precision="I32">
46
+ <dim>-1</dim>
47
+ </port>
48
+ <port id="3" precision="U8">
49
+ <dim>-1</dim>
50
+ </port>
51
+ </output>
52
+ </layer>
53
+ <layer id="5" name="Constant_951954" type="Const" version="opset1">
54
+ <data element_type="i32" shape="46" offset="1537480" size="184" />
55
+ <output>
56
+ <port id="0" precision="I32">
57
+ <dim>46</dim>
58
+ </port>
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="SentencepieceTokenizer_951955" type="SentencepieceTokenizer" version="extension">
62
+ <data nbest_size="0" alpha="0" add_bos="false" add_eos="false" reverse="false" />
63
+ <input>
64
+ <port id="0" precision="U8">
65
+ <dim>1536689</dim>
66
+ </port>
67
+ <port id="1" precision="STRING">
68
+ <dim>-1</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>-1</dim>
72
+ </port>
73
+ <port id="3" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ <port id="4" precision="U8">
77
+ <dim>-1</dim>
78
+ </port>
79
+ <port id="5" precision="I32">
80
+ <dim>46</dim>
81
+ </port>
82
+ </input>
83
+ <output>
84
+ <port id="6" precision="I64">
85
+ <dim>-1</dim>
86
+ <dim>2</dim>
87
+ </port>
88
+ <port id="7" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ <port id="8" precision="I64">
92
+ <dim>2</dim>
93
+ </port>
94
+ </output>
95
+ </layer>
96
+ <layer id="7" name="Broadcast_951957" type="Broadcast" version="opset3">
97
+ <data mode="numpy" />
98
+ <input>
99
+ <port id="0" precision="I32" />
100
+ <port id="1" precision="I64">
101
+ <dim>2</dim>
102
+ </port>
103
+ </input>
104
+ <output>
105
+ <port id="2" precision="I32">
106
+ <dim>-1</dim>
107
+ <dim>-1</dim>
108
+ </port>
109
+ </output>
110
+ </layer>
111
+ <layer id="8" name="Constant_951958" type="Const" version="opset1">
112
+ <data element_type="i32" shape="" offset="1537664" size="4" />
113
+ <output>
114
+ <port id="0" precision="I32" />
115
+ </output>
116
+ </layer>
117
+ <layer id="9" name="ShapeOf_951959" type="ShapeOf" version="opset3">
118
+ <data output_type="i64" />
119
+ <input>
120
+ <port id="0" precision="I32">
121
+ <dim>-1</dim>
122
+ </port>
123
+ </input>
124
+ <output>
125
+ <port id="1" precision="I64">
126
+ <dim>1</dim>
127
+ </port>
128
+ </output>
129
+ </layer>
130
+ <layer id="10" name="Broadcast_951960" type="Broadcast" version="opset3">
131
+ <data mode="numpy" />
132
+ <input>
133
+ <port id="0" precision="I32" />
134
+ <port id="1" precision="I64">
135
+ <dim>1</dim>
136
+ </port>
137
+ </input>
138
+ <output>
139
+ <port id="2" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ </output>
143
+ </layer>
144
+ <layer id="11" name="ScatterNDUpdate_951963" type="ScatterNDUpdate" version="opset4">
145
+ <input>
146
+ <port id="0" precision="I32">
147
+ <dim>-1</dim>
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="1" precision="I64">
151
+ <dim>-1</dim>
152
+ <dim>2</dim>
153
+ </port>
154
+ <port id="2" precision="I32">
155
+ <dim>-1</dim>
156
+ </port>
157
+ </input>
158
+ <output>
159
+ <port id="3" precision="I32">
160
+ <dim>-1</dim>
161
+ <dim>-1</dim>
162
+ </port>
163
+ </output>
164
+ </layer>
165
+ <layer id="12" name="Constant_951972" type="Const" version="opset1">
166
+ <data element_type="i64" shape="1" offset="1537668" size="8" />
167
+ <output>
168
+ <port id="0" precision="I64">
169
+ <dim>1</dim>
170
+ </port>
171
+ </output>
172
+ </layer>
173
+ <layer id="13" name="Constant_951973" type="Const" version="opset1">
174
+ <data element_type="i64" shape="1" offset="1537676" size="8" />
175
+ <output>
176
+ <port id="0" precision="I64">
177
+ <dim>1</dim>
178
+ </port>
179
+ </output>
180
+ </layer>
181
+ <layer id="14" name="Constant_951974" type="Const" version="opset1">
182
+ <data element_type="i64" shape="1" offset="1537684" size="8" />
183
+ <output>
184
+ <port id="0" precision="I64">
185
+ <dim>1</dim>
186
+ </port>
187
+ </output>
188
+ </layer>
189
+ <layer id="15" name="Constant_951975" type="Const" version="opset1">
190
+ <data element_type="i64" shape="1" offset="1537692" size="8" />
191
+ <output>
192
+ <port id="0" precision="I64">
193
+ <dim>1</dim>
194
+ </port>
195
+ </output>
196
+ </layer>
197
+ <layer id="16" name="Slice_951976" type="Slice" version="opset8">
198
+ <input>
199
+ <port id="0" precision="I32">
200
+ <dim>-1</dim>
201
+ <dim>-1</dim>
202
+ </port>
203
+ <port id="1" precision="I64">
204
+ <dim>1</dim>
205
+ </port>
206
+ <port id="2" precision="I64">
207
+ <dim>1</dim>
208
+ </port>
209
+ <port id="3" precision="I64">
210
+ <dim>1</dim>
211
+ </port>
212
+ <port id="4" precision="I64">
213
+ <dim>1</dim>
214
+ </port>
215
+ </input>
216
+ <output>
217
+ <port id="5" precision="I32">
218
+ <dim>-1</dim>
219
+ <dim>-1</dim>
220
+ </port>
221
+ </output>
222
+ </layer>
223
+ <layer id="17" name="Slice_951976" type="Convert" version="opset1">
224
+ <data destination_type="i64" />
225
+ <input>
226
+ <port id="0" precision="I32">
227
+ <dim>-1</dim>
228
+ <dim>-1</dim>
229
+ </port>
230
+ </input>
231
+ <output>
232
+ <port id="1" precision="I64" names="attention_mask">
233
+ <dim>-1</dim>
234
+ <dim>-1</dim>
235
+ </port>
236
+ </output>
237
+ </layer>
238
+ <layer id="19" name="Constant_951964" type="Const" version="opset1">
239
+ <data element_type="i32" shape="" offset="1537700" size="4" />
240
+ <output>
241
+ <port id="0" precision="I32" />
242
+ </output>
243
+ </layer>
244
+ <layer id="20" name="Broadcast_951965" type="Broadcast" version="opset3">
245
+ <data mode="bidirectional" />
246
+ <input>
247
+ <port id="0" precision="I32" />
248
+ <port id="1" precision="I64">
249
+ <dim>2</dim>
250
+ </port>
251
+ </input>
252
+ <output>
253
+ <port id="2" precision="I32">
254
+ <dim>-1</dim>
255
+ <dim>-1</dim>
256
+ </port>
257
+ </output>
258
+ </layer>
259
+ <layer id="21" name="ScatterNDUpdate_951966" type="ScatterNDUpdate" version="opset4">
260
+ <input>
261
+ <port id="0" precision="I32">
262
+ <dim>-1</dim>
263
+ <dim>-1</dim>
264
+ </port>
265
+ <port id="1" precision="I64">
266
+ <dim>-1</dim>
267
+ <dim>2</dim>
268
+ </port>
269
+ <port id="2" precision="I32">
270
+ <dim>-1</dim>
271
+ </port>
272
+ </input>
273
+ <output>
274
+ <port id="3" precision="I32">
275
+ <dim>-1</dim>
276
+ <dim>-1</dim>
277
+ </port>
278
+ </output>
279
+ </layer>
280
+ <layer id="22" name="Constant_951967" type="Const" version="opset1">
281
+ <data element_type="i64" shape="1" offset="1537668" size="8" />
282
+ <output>
283
+ <port id="0" precision="I64">
284
+ <dim>1</dim>
285
+ </port>
286
+ </output>
287
+ </layer>
288
+ <layer id="23" name="Constant_951968" type="Const" version="opset1">
289
+ <data element_type="i64" shape="1" offset="1537676" size="8" />
290
+ <output>
291
+ <port id="0" precision="I64">
292
+ <dim>1</dim>
293
+ </port>
294
+ </output>
295
+ </layer>
296
+ <layer id="24" name="Constant_951969" type="Const" version="opset1">
297
+ <data element_type="i64" shape="1" offset="1537684" size="8" />
298
+ <output>
299
+ <port id="0" precision="I64">
300
+ <dim>1</dim>
301
+ </port>
302
+ </output>
303
+ </layer>
304
+ <layer id="25" name="Constant_951970" type="Const" version="opset1">
305
+ <data element_type="i64" shape="1" offset="1537692" size="8" />
306
+ <output>
307
+ <port id="0" precision="I64">
308
+ <dim>1</dim>
309
+ </port>
310
+ </output>
311
+ </layer>
312
+ <layer id="26" name="Slice_951971" type="Slice" version="opset8">
313
+ <input>
314
+ <port id="0" precision="I32">
315
+ <dim>-1</dim>
316
+ <dim>-1</dim>
317
+ </port>
318
+ <port id="1" precision="I64">
319
+ <dim>1</dim>
320
+ </port>
321
+ <port id="2" precision="I64">
322
+ <dim>1</dim>
323
+ </port>
324
+ <port id="3" precision="I64">
325
+ <dim>1</dim>
326
+ </port>
327
+ <port id="4" precision="I64">
328
+ <dim>1</dim>
329
+ </port>
330
+ </input>
331
+ <output>
332
+ <port id="5" precision="I32">
333
+ <dim>-1</dim>
334
+ <dim>-1</dim>
335
+ </port>
336
+ </output>
337
+ </layer>
338
+ <layer id="27" name="Slice_951971" type="Convert" version="opset1">
339
+ <data destination_type="i64" />
340
+ <input>
341
+ <port id="0" precision="I32">
342
+ <dim>-1</dim>
343
+ <dim>-1</dim>
344
+ </port>
345
+ </input>
346
+ <output>
347
+ <port id="1" precision="I64" names="input_ids">
348
+ <dim>-1</dim>
349
+ <dim>-1</dim>
350
+ </port>
351
+ </output>
352
+ </layer>
353
+ <layer id="28" name="Result_951977" type="Result" version="opset1">
354
+ <input>
355
+ <port id="0" precision="I64">
356
+ <dim>-1</dim>
357
+ <dim>-1</dim>
358
+ </port>
359
+ </input>
360
+ </layer>
361
+ <layer id="18" name="Result_951978" type="Result" version="opset1">
362
+ <input>
363
+ <port id="0" precision="I64">
364
+ <dim>-1</dim>
365
+ <dim>-1</dim>
366
+ </port>
367
+ </input>
368
+ </layer>
369
+ </layers>
370
+ <edges>
371
+ <edge from-layer="0" from-port="0" to-layer="6" to-port="1" />
372
+ <edge from-layer="1" from-port="0" to-layer="7" to-port="0" />
373
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="0" />
374
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
375
+ <edge from-layer="4" from-port="1" to-layer="6" to-port="2" />
376
+ <edge from-layer="4" from-port="2" to-layer="6" to-port="3" />
377
+ <edge from-layer="4" from-port="3" to-layer="6" to-port="4" />
378
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="5" />
379
+ <edge from-layer="6" from-port="8" to-layer="20" to-port="1" />
380
+ <edge from-layer="6" from-port="6" to-layer="21" to-port="1" />
381
+ <edge from-layer="6" from-port="7" to-layer="21" to-port="2" />
382
+ <edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
383
+ <edge from-layer="6" from-port="7" to-layer="9" to-port="0" />
384
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="1" />
385
+ <edge from-layer="7" from-port="2" to-layer="11" to-port="0" />
386
+ <edge from-layer="8" from-port="0" to-layer="10" to-port="0" />
387
+ <edge from-layer="9" from-port="1" to-layer="10" to-port="1" />
388
+ <edge from-layer="10" from-port="2" to-layer="11" to-port="2" />
389
+ <edge from-layer="11" from-port="3" to-layer="16" to-port="0" />
390
+ <edge from-layer="12" from-port="0" to-layer="16" to-port="1" />
391
+ <edge from-layer="13" from-port="0" to-layer="16" to-port="2" />
392
+ <edge from-layer="14" from-port="0" to-layer="16" to-port="3" />
393
+ <edge from-layer="15" from-port="0" to-layer="16" to-port="4" />
394
+ <edge from-layer="16" from-port="5" to-layer="17" to-port="0" />
395
+ <edge from-layer="17" from-port="1" to-layer="18" to-port="0" />
396
+ <edge from-layer="19" from-port="0" to-layer="20" to-port="0" />
397
+ <edge from-layer="20" from-port="2" to-layer="21" to-port="0" />
398
+ <edge from-layer="21" from-port="3" to-layer="26" to-port="0" />
399
+ <edge from-layer="22" from-port="0" to-layer="26" to-port="1" />
400
+ <edge from-layer="23" from-port="0" to-layer="26" to-port="2" />
401
+ <edge from-layer="24" from-port="0" to-layer="26" to-port="3" />
402
+ <edge from-layer="25" from-port="0" to-layer="26" to-port="4" />
403
+ <edge from-layer="26" from-port="5" to-layer="27" to-port="0" />
404
+ <edge from-layer="27" from-port="1" to-layer="28" to-port="0" />
405
+ </edges>
406
+ <rt_info>
407
+ <add_attention_mask value="True" />
408
+ <add_prefix_space />
409
+ <add_special_tokens value="True" />
410
+ <bos_token_id value="1" />
411
+ <chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are OpenCoder, created by OpenCoder Team.&lt;|im_end|>&#10;' }}{% endif %}{{'&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;'}}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
412
+ <clean_up_tokenization_spaces value="False" />
413
+ <detokenizer_input_type value="i64" />
414
+ <eos_token_id value="2" />
415
+ <handle_special_tokens_with_re value="True" />
416
+ <number_of_inputs value="1" />
417
+ <openvino_tokenizers_version value="2024.5.0.0.dev20241030" />
418
+ <openvino_version value="2024.5.0.dev20241030" />
419
+ <original_tokenizer_class value="&lt;class 'transformers_modules.infly.OpenCoder-1.5B-Instruct.726eaa2df918903ab279981653644bb8e8e04e85.tokenization_inflm.INFLMTokenizer'>" />
420
+ <pad_token_id value="3" />
421
+ <sentencepiece_version value="0.2.0" />
422
+ <skip_special_tokens value="True" />
423
+ <streaming_detokenizer value="False" />
424
+ <tiktoken_version value="0.8.0" />
425
+ <tokenizer_output_type value="i64" />
426
+ <tokenizers_version value="0.20.1" />
427
+ <transformers_version value="4.45.2" />
428
+ <use_max_padding value="False" />
429
+ <use_sentencepiece_backend value="False" />
430
+ <utf8_replace_mode />
431
+ <with_detokenizer value="True" />
432
+ </rt_info>
433
+ </net>