Hugging Face's logo

AIFunOver
/
DeepSeek-R1-Distill-Qwen-32B-openvino-4bit

Text Generation
Transformers
Safetensors
OpenVINO
qwen2
nncf
4-bit precision
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
AIFunOver commited on
Commit
67887be
·
verified ·
1 Parent(s): d6793fb

Upload openvino_tokenizer.xml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openvino_tokenizer.xml +813 -0
openvino_tokenizer.xml ADDED
@@ -0,0 +1,813 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_4778707" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_4778707">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_4778806" 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_4778807" type="Const" version="opset1">
19
+ <data element_type="i32" shape="" offset="4" size="4" />
20
+ <output>
21
+ <port id="0" precision="I32" />
22
+ </output>
23
+ </layer>
24
+ <layer id="3" name="Constant_4778808" type="Const" version="opset1">
25
+ <data element_type="i32" shape="1" offset="8" size="4" />
26
+ <output>
27
+ <port id="0" precision="I32">
28
+ <dim>1</dim>
29
+ </port>
30
+ </output>
31
+ </layer>
32
+ <layer id="4" name="Constant_4778713" type="Const" version="opset1">
33
+ <data element_type="i64" shape="" offset="12" size="8" />
34
+ <output>
35
+ <port id="0" precision="I64" />
36
+ </output>
37
+ </layer>
38
+ <layer id="5" name="StringTensorUnpack_4778708" type="StringTensorUnpack" version="extension">
39
+ <data mode="begins_ends" />
40
+ <input>
41
+ <port id="0" precision="STRING">
42
+ <dim>-1</dim>
43
+ </port>
44
+ </input>
45
+ <output>
46
+ <port id="1" precision="I32">
47
+ <dim>-1</dim>
48
+ </port>
49
+ <port id="2" precision="I32">
50
+ <dim>-1</dim>
51
+ </port>
52
+ <port id="3" precision="U8">
53
+ <dim>-1</dim>
54
+ </port>
55
+ </output>
56
+ </layer>
57
+ <layer id="6" name="ShapeOf_4778709" type="ShapeOf" version="opset3">
58
+ <data output_type="i64" />
59
+ <input>
60
+ <port id="0" precision="I32">
61
+ <dim>-1</dim>
62
+ </port>
63
+ </input>
64
+ <output>
65
+ <port id="1" precision="I64">
66
+ <dim>1</dim>
67
+ </port>
68
+ </output>
69
+ </layer>
70
+ <layer id="7" name="Constant_4778710" type="Const" version="opset1">
71
+ <data element_type="i64" shape="" offset="12" size="8" />
72
+ <output>
73
+ <port id="0" precision="I64" />
74
+ </output>
75
+ </layer>
76
+ <layer id="8" name="Constant_4778711" type="Const" version="opset1">
77
+ <data element_type="i64" shape="" offset="12" size="8" />
78
+ <output>
79
+ <port id="0" precision="I64" />
80
+ </output>
81
+ </layer>
82
+ <layer id="9" name="Gather_4778712" type="Gather" version="opset8">
83
+ <data batch_dims="0" />
84
+ <input>
85
+ <port id="0" precision="I64">
86
+ <dim>1</dim>
87
+ </port>
88
+ <port id="1" precision="I64" />
89
+ <port id="2" precision="I64" />
90
+ </input>
91
+ <output>
92
+ <port id="3" precision="I64" />
93
+ </output>
94
+ </layer>
95
+ <layer id="10" name="Constant_4778714" type="Const" version="opset1">
96
+ <data element_type="i64" shape="" offset="20" size="8" />
97
+ <output>
98
+ <port id="0" precision="I64" />
99
+ </output>
100
+ </layer>
101
+ <layer id="11" name="Range_4778715" type="Range" version="opset4">
102
+ <data output_type="i32" />
103
+ <input>
104
+ <port id="0" precision="I64" />
105
+ <port id="1" precision="I64" />
106
+ <port id="2" precision="I64" />
107
+ </input>
108
+ <output>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="12" name="Constant_4778716" type="Const" version="opset1">
115
+ <data element_type="i64" shape="" offset="20" size="8" />
116
+ <output>
117
+ <port id="0" precision="I64" />
118
+ </output>
119
+ </layer>
120
+ <layer id="13" name="Constant_4778717" type="Const" version="opset1">
121
+ <data element_type="i64" shape="" offset="20" size="8" />
122
+ <output>
123
+ <port id="0" precision="I64" />
124
+ </output>
125
+ </layer>
126
+ <layer id="14" name="Add_4778718" type="Add" version="opset1">
127
+ <data auto_broadcast="numpy" />
128
+ <input>
129
+ <port id="0" precision="I64" />
130
+ <port id="1" precision="I64" />
131
+ </input>
132
+ <output>
133
+ <port id="2" precision="I64" />
134
+ </output>
135
+ </layer>
136
+ <layer id="15" name="Constant_4778719" type="Const" version="opset1">
137
+ <data element_type="i64" shape="" offset="20" size="8" />
138
+ <output>
139
+ <port id="0" precision="I64" />
140
+ </output>
141
+ </layer>
142
+ <layer id="16" name="Range_4778720" type="Range" version="opset4">
143
+ <data output_type="i32" />
144
+ <input>
145
+ <port id="0" precision="I64" />
146
+ <port id="1" precision="I64" />
147
+ <port id="2" precision="I64" />
148
+ </input>
149
+ <output>
150
+ <port id="3" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ </output>
154
+ </layer>
155
+ <layer id="17" name="Constant_4778782" type="Const" version="opset1">
156
+ <data element_type="u8" shape="455" offset="28" size="455" />
157
+ <output>
158
+ <port id="0" precision="U8">
159
+ <dim>455</dim>
160
+ </port>
161
+ </output>
162
+ </layer>
163
+ <layer id="18" name="SpecialTokensSplit_4778783" type="SpecialTokensSplit" version="extension">
164
+ <input>
165
+ <port id="0" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ <port id="1" precision="I32">
169
+ <dim>-1</dim>
170
+ </port>
171
+ <port id="2" precision="I32">
172
+ <dim>-1</dim>
173
+ </port>
174
+ <port id="3" precision="I32">
175
+ <dim>-1</dim>
176
+ </port>
177
+ <port id="4" precision="U8">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="5" precision="U8">
181
+ <dim>455</dim>
182
+ </port>
183
+ </input>
184
+ <output>
185
+ <port id="6" precision="I32">
186
+ <dim>-1</dim>
187
+ </port>
188
+ <port id="7" precision="I32">
189
+ <dim>-1</dim>
190
+ </port>
191
+ <port id="8" precision="I32">
192
+ <dim>-1</dim>
193
+ </port>
194
+ <port id="9" precision="I32">
195
+ <dim>-1</dim>
196
+ </port>
197
+ <port id="10" precision="U8">
198
+ <dim>-1</dim>
199
+ </port>
200
+ <port id="11" precision="BOOL">
201
+ <dim>-1</dim>
202
+ </port>
203
+ </output>
204
+ </layer>
205
+ <layer id="19" name="NormalizeUnicode_4778784" type="NormalizeUnicode" version="extension">
206
+ <data normalization_form="NFC" />
207
+ <input>
208
+ <port id="0" precision="I32">
209
+ <dim>-1</dim>
210
+ </port>
211
+ <port id="1" precision="I32">
212
+ <dim>-1</dim>
213
+ </port>
214
+ <port id="2" precision="U8">
215
+ <dim>-1</dim>
216
+ </port>
217
+ <port id="3" precision="BOOL">
218
+ <dim>-1</dim>
219
+ </port>
220
+ </input>
221
+ <output>
222
+ <port id="4" precision="I32">
223
+ <dim>-1</dim>
224
+ </port>
225
+ <port id="5" precision="I32">
226
+ <dim>-1</dim>
227
+ </port>
228
+ <port id="6" precision="U8">
229
+ <dim>-1</dim>
230
+ </port>
231
+ <port id="7" precision="BOOL">
232
+ <dim>-1</dim>
233
+ </port>
234
+ </output>
235
+ </layer>
236
+ <layer id="20" name="Constant_4778786" type="Const" version="opset1">
237
+ <data element_type="u8" shape="110" offset="483" size="110" />
238
+ <output>
239
+ <port id="0" precision="U8">
240
+ <dim>110</dim>
241
+ </port>
242
+ </output>
243
+ </layer>
244
+ <layer id="21" name="RegexSplit_4778787" type="RegexSplit" version="extension">
245
+ <data behaviour="isolate" invert="false" max_splits="-1" />
246
+ <input>
247
+ <port id="0" precision="I32">
248
+ <dim>-1</dim>
249
+ </port>
250
+ <port id="1" precision="I32">
251
+ <dim>-1</dim>
252
+ </port>
253
+ <port id="2" precision="I32">
254
+ <dim>-1</dim>
255
+ </port>
256
+ <port id="3" precision="I32">
257
+ <dim>-1</dim>
258
+ </port>
259
+ <port id="4" precision="U8">
260
+ <dim>-1</dim>
261
+ </port>
262
+ <port id="5" precision="BOOL">
263
+ <dim>-1</dim>
264
+ </port>
265
+ <port id="6" precision="U8">
266
+ <dim>110</dim>
267
+ </port>
268
+ </input>
269
+ <output>
270
+ <port id="7" precision="I32">
271
+ <dim>-1</dim>
272
+ </port>
273
+ <port id="8" precision="I32">
274
+ <dim>-1</dim>
275
+ </port>
276
+ <port id="9" precision="I32">
277
+ <dim>-1</dim>
278
+ </port>
279
+ <port id="10" precision="I32">
280
+ <dim>-1</dim>
281
+ </port>
282
+ <port id="11" precision="U8">
283
+ <dim>-1</dim>
284
+ </port>
285
+ <port id="12" precision="BOOL">
286
+ <dim>-1</dim>
287
+ </port>
288
+ </output>
289
+ </layer>
290
+ <layer id="22" name="Constant_4778789" type="Const" version="opset1">
291
+ <data element_type="u8" shape="1582941" offset="593" size="1582941" />
292
+ <output>
293
+ <port id="0" precision="U8">
294
+ <dim>1582941</dim>
295
+ </port>
296
+ </output>
297
+ </layer>
298
+ <layer id="23" name="StringTensorUnpack_4778790" type="StringTensorUnpack" version="extension">
299
+ <data mode="begins_ends" />
300
+ <input>
301
+ <port id="0" precision="U8">
302
+ <dim>1582941</dim>
303
+ </port>
304
+ </input>
305
+ <output>
306
+ <port id="1" precision="I32">
307
+ <dim>-1</dim>
308
+ </port>
309
+ <port id="2" precision="I32">
310
+ <dim>-1</dim>
311
+ </port>
312
+ <port id="3" precision="U8">
313
+ <dim>-1</dim>
314
+ </port>
315
+ </output>
316
+ </layer>
317
+ <layer id="24" name="Constant_4778795" type="Const" version="opset1">
318
+ <data element_type="u8" shape="1096915" offset="1583534" size="1096915" />
319
+ <output>
320
+ <port id="0" precision="U8">
321
+ <dim>1096915</dim>
322
+ </port>
323
+ </output>
324
+ </layer>
325
+ <layer id="25" name="StringTensorUnpack_4778796" type="StringTensorUnpack" version="extension">
326
+ <data mode="begins_ends" />
327
+ <input>
328
+ <port id="0" precision="U8">
329
+ <dim>1096915</dim>
330
+ </port>
331
+ </input>
332
+ <output>
333
+ <port id="1" precision="I32">
334
+ <dim>-1</dim>
335
+ </port>
336
+ <port id="2" precision="I32">
337
+ <dim>-1</dim>
338
+ </port>
339
+ <port id="3" precision="U8">
340
+ <dim>-1</dim>
341
+ </port>
342
+ </output>
343
+ </layer>
344
+ <layer id="26" name="Constant_4778798" type="Const" version="opset1">
345
+ <data element_type="u8" shape="1089910" offset="2680449" size="1089910" />
346
+ <output>
347
+ <port id="0" precision="U8">
348
+ <dim>1089910</dim>
349
+ </port>
350
+ </output>
351
+ </layer>
352
+ <layer id="27" name="StringTensorUnpack_4778799" type="StringTensorUnpack" version="extension">
353
+ <data mode="begins_ends" />
354
+ <input>
355
+ <port id="0" precision="U8">
356
+ <dim>1089910</dim>
357
+ </port>
358
+ </input>
359
+ <output>
360
+ <port id="1" precision="I32">
361
+ <dim>-1</dim>
362
+ </port>
363
+ <port id="2" precision="I32">
364
+ <dim>-1</dim>
365
+ </port>
366
+ <port id="3" precision="U8">
367
+ <dim>-1</dim>
368
+ </port>
369
+ </output>
370
+ </layer>
371
+ <layer id="28" name="Constant_4778792" type="Const" version="opset1">
372
+ <data element_type="u8" shape="400" offset="3770359" size="400" />
373
+ <output>
374
+ <port id="0" precision="U8">
375
+ <dim>400</dim>
376
+ </port>
377
+ </output>
378
+ </layer>
379
+ <layer id="29" name="StringTensorUnpack_4778793" type="StringTensorUnpack" version="extension">
380
+ <data mode="begins_ends" />
381
+ <input>
382
+ <port id="0" precision="U8">
383
+ <dim>400</dim>
384
+ </port>
385
+ </input>
386
+ <output>
387
+ <port id="1" precision="I32">
388
+ <dim>-1</dim>
389
+ </port>
390
+ <port id="2" precision="I32">
391
+ <dim>-1</dim>
392
+ </port>
393
+ <port id="3" precision="U8">
394
+ <dim>-1</dim>
395
+ </port>
396
+ </output>
397
+ </layer>
398
+ <layer id="30" name="Constant_4778800" type="Const" version="opset1">
399
+ <data element_type="i32" shape="22" offset="3770759" size="88" />
400
+ <output>
401
+ <port id="0" precision="I32">
402
+ <dim>22</dim>
403
+ </port>
404
+ </output>
405
+ </layer>
406
+ <layer id="31" name="BPETokenizer_4778801" type="BPETokenizer" version="extension">
407
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
408
+ <input>
409
+ <port id="0" precision="I32">
410
+ <dim>-1</dim>
411
+ </port>
412
+ <port id="1" precision="I32">
413
+ <dim>-1</dim>
414
+ </port>
415
+ <port id="2" precision="I32">
416
+ <dim>-1</dim>
417
+ </port>
418
+ <port id="3" precision="I32">
419
+ <dim>-1</dim>
420
+ </port>
421
+ <port id="4" precision="U8">
422
+ <dim>-1</dim>
423
+ </port>
424
+ <port id="5" precision="I32">
425
+ <dim>-1</dim>
426
+ </port>
427
+ <port id="6" precision="I32">
428
+ <dim>-1</dim>
429
+ </port>
430
+ <port id="7" precision="U8">
431
+ <dim>-1</dim>
432
+ </port>
433
+ <port id="8" precision="I32">
434
+ <dim>-1</dim>
435
+ </port>
436
+ <port id="9" precision="I32">
437
+ <dim>-1</dim>
438
+ </port>
439
+ <port id="10" precision="U8">
440
+ <dim>-1</dim>
441
+ </port>
442
+ <port id="11" precision="I32">
443
+ <dim>-1</dim>
444
+ </port>
445
+ <port id="12" precision="I32">
446
+ <dim>-1</dim>
447
+ </port>
448
+ <port id="13" precision="U8">
449
+ <dim>-1</dim>
450
+ </port>
451
+ <port id="14" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ <port id="15" precision="I32">
455
+ <dim>-1</dim>
456
+ </port>
457
+ <port id="16" precision="U8">
458
+ <dim>-1</dim>
459
+ </port>
460
+ <port id="17" precision="I32">
461
+ <dim>22</dim>
462
+ </port>
463
+ </input>
464
+ <output>
465
+ <port id="18" precision="I32">
466
+ <dim>-1</dim>
467
+ </port>
468
+ <port id="19" precision="I32">
469
+ <dim>-1</dim>
470
+ </port>
471
+ <port id="20" precision="I32">
472
+ <dim>-1</dim>
473
+ </port>
474
+ </output>
475
+ </layer>
476
+ <layer id="32" name="Subtract_4778802" type="Subtract" version="opset1">
477
+ <data auto_broadcast="numpy" />
478
+ <input>
479
+ <port id="0" precision="I32">
480
+ <dim>-1</dim>
481
+ </port>
482
+ <port id="1" precision="I32">
483
+ <dim>-1</dim>
484
+ </port>
485
+ </input>
486
+ <output>
487
+ <port id="2" precision="I32">
488
+ <dim>-1</dim>
489
+ </port>
490
+ </output>
491
+ </layer>
492
+ <layer id="33" name="Constant_4778803" type="Const" version="opset1">
493
+ <data element_type="i32" shape="" offset="3770847" size="4" />
494
+ <output>
495
+ <port id="0" precision="I32" />
496
+ </output>
497
+ </layer>
498
+ <layer id="34" name="Minimum_4778804" type="Minimum" version="opset1">
499
+ <data auto_broadcast="numpy" />
500
+ <input>
501
+ <port id="0" precision="I32">
502
+ <dim>-1</dim>
503
+ </port>
504
+ <port id="1" precision="I32" />
505
+ </input>
506
+ <output>
507
+ <port id="2" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ </output>
511
+ </layer>
512
+ <layer id="35" name="Add_4778805" type="Add" version="opset1">
513
+ <data auto_broadcast="numpy" />
514
+ <input>
515
+ <port id="0" precision="I32">
516
+ <dim>-1</dim>
517
+ </port>
518
+ <port id="1" precision="I32">
519
+ <dim>-1</dim>
520
+ </port>
521
+ </input>
522
+ <output>
523
+ <port id="2" precision="I32">
524
+ <dim>-1</dim>
525
+ </port>
526
+ </output>
527
+ </layer>
528
+ <layer id="36" name="Constant_4778809" type="Const" version="opset1">
529
+ <data element_type="i32" shape="2" offset="12" size="8" />
530
+ <output>
531
+ <port id="0" precision="I32">
532
+ <dim>2</dim>
533
+ </port>
534
+ </output>
535
+ </layer>
536
+ <layer id="37" name="CombineSegments_4778810" type="CombineSegments" version="extension">
537
+ <input>
538
+ <port id="0" precision="I32" />
539
+ <port id="1" precision="I32" />
540
+ <port id="2" precision="I32">
541
+ <dim>1</dim>
542
+ </port>
543
+ <port id="3" precision="I32">
544
+ <dim>-1</dim>
545
+ </port>
546
+ <port id="4" precision="I32">
547
+ <dim>-1</dim>
548
+ </port>
549
+ <port id="5" precision="I32">
550
+ <dim>-1</dim>
551
+ </port>
552
+ <port id="6" precision="I32">
553
+ <dim>2</dim>
554
+ </port>
555
+ </input>
556
+ <output>
557
+ <port id="7" precision="I32">
558
+ <dim>-1</dim>
559
+ </port>
560
+ <port id="8" precision="I32">
561
+ <dim>-1</dim>
562
+ </port>
563
+ <port id="9" precision="I32">
564
+ <dim>-1</dim>
565
+ </port>
566
+ <port id="10" precision="I32">
567
+ <dim>-1</dim>
568
+ </port>
569
+ <port id="11" precision="I32">
570
+ <dim>-1</dim>
571
+ </port>
572
+ <port id="12" precision="I32">
573
+ <dim>-1</dim>
574
+ </port>
575
+ </output>
576
+ </layer>
577
+ <layer id="38" name="Subtract_4778811" type="Subtract" version="opset1">
578
+ <data auto_broadcast="numpy" />
579
+ <input>
580
+ <port id="0" precision="I32">
581
+ <dim>-1</dim>
582
+ </port>
583
+ <port id="1" precision="I32">
584
+ <dim>-1</dim>
585
+ </port>
586
+ </input>
587
+ <output>
588
+ <port id="2" precision="I32">
589
+ <dim>-1</dim>
590
+ </port>
591
+ </output>
592
+ </layer>
593
+ <layer id="39" name="Constant_4778812" type="Const" version="opset1">
594
+ <data element_type="i32" shape="" offset="0" size="4" />
595
+ <output>
596
+ <port id="0" precision="I32" />
597
+ </output>
598
+ </layer>
599
+ <layer id="40" name="ReduceMax_4778813" type="ReduceMax" version="opset1">
600
+ <data keep_dims="false" />
601
+ <input>
602
+ <port id="0" precision="I32">
603
+ <dim>-1</dim>
604
+ </port>
605
+ <port id="1" precision="I32" />
606
+ </input>
607
+ <output>
608
+ <port id="2" precision="I32" />
609
+ </output>
610
+ </layer>
611
+ <layer id="41" name="Constant_4778814" type="Const" version="opset1">
612
+ <data element_type="i32" shape="" offset="3770851" size="4" />
613
+ <output>
614
+ <port id="0" precision="I32" />
615
+ </output>
616
+ </layer>
617
+ <layer id="42" name="RaggedToDense_4778815" type="RaggedToDense" version="extension">
618
+ <data pad_right="false" />
619
+ <input>
620
+ <port id="0" precision="I32">
621
+ <dim>-1</dim>
622
+ </port>
623
+ <port id="1" precision="I32">
624
+ <dim>-1</dim>
625
+ </port>
626
+ <port id="2" precision="I32">
627
+ <dim>-1</dim>
628
+ </port>
629
+ <port id="3" precision="I32" />
630
+ <port id="4" precision="I32" />
631
+ </input>
632
+ <output>
633
+ <port id="5" precision="I32">
634
+ <dim>-1</dim>
635
+ <dim>-1</dim>
636
+ </port>
637
+ <port id="6" precision="BOOL">
638
+ <dim>-1</dim>
639
+ <dim>-1</dim>
640
+ </port>
641
+ </output>
642
+ </layer>
643
+ <layer id="43" name="Convert_4778816" type="Convert" version="opset1">
644
+ <data destination_type="i32" />
645
+ <input>
646
+ <port id="0" precision="BOOL">
647
+ <dim>-1</dim>
648
+ <dim>-1</dim>
649
+ </port>
650
+ </input>
651
+ <output>
652
+ <port id="1" precision="I32">
653
+ <dim>-1</dim>
654
+ <dim>-1</dim>
655
+ </port>
656
+ </output>
657
+ </layer>
658
+ <layer id="44" name="Convert_4778816.0" type="Convert" version="opset1">
659
+ <data destination_type="i64" />
660
+ <input>
661
+ <port id="0" precision="I32">
662
+ <dim>-1</dim>
663
+ <dim>-1</dim>
664
+ </port>
665
+ </input>
666
+ <output>
667
+ <port id="1" precision="I64" names="attention_mask">
668
+ <dim>-1</dim>
669
+ <dim>-1</dim>
670
+ </port>
671
+ </output>
672
+ </layer>
673
+ <layer id="46" name="RaggedToDense_4778815.0" type="Convert" version="opset1">
674
+ <data destination_type="i64" />
675
+ <input>
676
+ <port id="0" precision="I32">
677
+ <dim>-1</dim>
678
+ <dim>-1</dim>
679
+ </port>
680
+ </input>
681
+ <output>
682
+ <port id="1" precision="I64" names="input_ids">
683
+ <dim>-1</dim>
684
+ <dim>-1</dim>
685
+ </port>
686
+ </output>
687
+ </layer>
688
+ <layer id="47" name="Result_4778819" type="Result" version="opset1">
689
+ <input>
690
+ <port id="0" precision="I64">
691
+ <dim>-1</dim>
692
+ <dim>-1</dim>
693
+ </port>
694
+ </input>
695
+ </layer>
696
+ <layer id="45" name="Result_4778821" type="Result" version="opset1">
697
+ <input>
698
+ <port id="0" precision="I64">
699
+ <dim>-1</dim>
700
+ <dim>-1</dim>
701
+ </port>
702
+ </input>
703
+ </layer>
704
+ </layers>
705
+ <edges>
706
+ <edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
707
+ <edge from-layer="1" from-port="0" to-layer="37" to-port="0" />
708
+ <edge from-layer="2" from-port="0" to-layer="37" to-port="1" />
709
+ <edge from-layer="3" from-port="0" to-layer="37" to-port="2" />
710
+ <edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
711
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
712
+ <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
713
+ <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
714
+ <edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
715
+ <edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
716
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
717
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
718
+ <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
719
+ <edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
720
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
721
+ <edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
722
+ <edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
723
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
724
+ <edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
725
+ <edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
726
+ <edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
727
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
728
+ <edge from-layer="18" from-port="9" to-layer="19" to-port="1" />
729
+ <edge from-layer="18" from-port="7" to-layer="21" to-port="1" />
730
+ <edge from-layer="18" from-port="6" to-layer="21" to-port="0" />
731
+ <edge from-layer="18" from-port="8" to-layer="19" to-port="0" />
732
+ <edge from-layer="18" from-port="10" to-layer="19" to-port="2" />
733
+ <edge from-layer="18" from-port="11" to-layer="19" to-port="3" />
734
+ <edge from-layer="19" from-port="4" to-layer="21" to-port="2" />
735
+ <edge from-layer="19" from-port="7" to-layer="21" to-port="5" />
736
+ <edge from-layer="19" from-port="6" to-layer="21" to-port="4" />
737
+ <edge from-layer="19" from-port="5" to-layer="21" to-port="3" />
738
+ <edge from-layer="20" from-port="0" to-layer="21" to-port="6" />
739
+ <edge from-layer="21" from-port="7" to-layer="31" to-port="0" />
740
+ <edge from-layer="21" from-port="8" to-layer="31" to-port="1" />
741
+ <edge from-layer="21" from-port="9" to-layer="31" to-port="2" />
742
+ <edge from-layer="21" from-port="10" to-layer="31" to-port="3" />
743
+ <edge from-layer="21" from-port="11" to-layer="31" to-port="4" />
744
+ <edge from-layer="22" from-port="0" to-layer="23" to-port="0" />
745
+ <edge from-layer="23" from-port="1" to-layer="31" to-port="5" />
746
+ <edge from-layer="23" from-port="3" to-layer="31" to-port="7" />
747
+ <edge from-layer="23" from-port="2" to-layer="31" to-port="6" />
748
+ <edge from-layer="24" from-port="0" to-layer="25" to-port="0" />
749
+ <edge from-layer="25" from-port="1" to-layer="31" to-port="8" />
750
+ <edge from-layer="25" from-port="3" to-layer="31" to-port="10" />
751
+ <edge from-layer="25" from-port="2" to-layer="31" to-port="9" />
752
+ <edge from-layer="26" from-port="0" to-layer="27" to-port="0" />
753
+ <edge from-layer="27" from-port="1" to-layer="31" to-port="11" />
754
+ <edge from-layer="27" from-port="2" to-layer="31" to-port="12" />
755
+ <edge from-layer="27" from-port="3" to-layer="31" to-port="13" />
756
+ <edge from-layer="28" from-port="0" to-layer="29" to-port="0" />
757
+ <edge from-layer="29" from-port="1" to-layer="31" to-port="14" />
758
+ <edge from-layer="29" from-port="2" to-layer="31" to-port="15" />
759
+ <edge from-layer="29" from-port="3" to-layer="31" to-port="16" />
760
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="17" />
761
+ <edge from-layer="31" from-port="18" to-layer="37" to-port="3" />
762
+ <edge from-layer="31" from-port="20" to-layer="37" to-port="5" />
763
+ <edge from-layer="31" from-port="18" to-layer="35" to-port="0" />
764
+ <edge from-layer="31" from-port="18" to-layer="32" to-port="1" />
765
+ <edge from-layer="31" from-port="19" to-layer="32" to-port="0" />
766
+ <edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
767
+ <edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
768
+ <edge from-layer="34" from-port="2" to-layer="35" to-port="1" />
769
+ <edge from-layer="35" from-port="2" to-layer="37" to-port="4" />
770
+ <edge from-layer="36" from-port="0" to-layer="37" to-port="6" />
771
+ <edge from-layer="37" from-port="8" to-layer="38" to-port="0" />
772
+ <edge from-layer="37" from-port="7" to-layer="38" to-port="1" />
773
+ <edge from-layer="37" from-port="7" to-layer="42" to-port="0" />
774
+ <edge from-layer="37" from-port="8" to-layer="42" to-port="1" />
775
+ <edge from-layer="37" from-port="9" to-layer="42" to-port="2" />
776
+ <edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
777
+ <edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
778
+ <edge from-layer="40" from-port="2" to-layer="42" to-port="3" />
779
+ <edge from-layer="41" from-port="0" to-layer="42" to-port="4" />
780
+ <edge from-layer="42" from-port="6" to-layer="43" to-port="0" />
781
+ <edge from-layer="42" from-port="5" to-layer="46" to-port="0" />
782
+ <edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
783
+ <edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
784
+ <edge from-layer="46" from-port="1" to-layer="47" to-port="0" />
785
+ </edges>
786
+ <rt_info>
787
+ <add_attention_mask value="True" />
788
+ <add_prefix_space />
789
+ <add_special_tokens value="True" />
790
+ <bos_token_id value="151646" />
791
+ <chat_template value="{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'&lt;｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'&lt;｜Assistant｜>&lt;｜tool▁calls▁begin｜>&lt;｜tool▁call▁begin｜>' + tool['type'] + '&lt;｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '&lt;｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '&lt;｜tool▁call▁begin｜>' + tool['type'] + '&lt;｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '&lt;｜tool▁call▁end｜>'}}{{'&lt;｜tool▁calls▁end｜>&lt;｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'&lt;｜tool▁outputs▁end｜>' + message['content'] + '&lt;｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '&lt;/think>' in content %}{% set content = content.split('&lt;/think>')[-1] %}{% endif %}{{'&lt;｜Assistant｜>' + content + '&lt;｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'&lt;｜tool▁outputs▁begin｜>&lt;｜tool▁output▁begin｜>' + message['content'] + '&lt;｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n&lt;｜tool▁output▁begin｜>' + message['content'] + '&lt;｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'&lt;｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'&lt;｜Assistant｜>'}}{% endif %}" />
792
+ <clean_up_tokenization_spaces />
793
+ <detokenizer_input_type value="i64" />
794
+ <eos_token_id value="151643" />
795
+ <handle_special_tokens_with_re />
796
+ <number_of_inputs value="1" />
797
+ <openvino_tokenizers_version value="2025.0.0.0.dev20250113" />
798
+ <openvino_version value="2025.0.0.dev20250113" />
799
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
800
+ <pad_token_id value="151643" />
801
+ <sentencepiece_version value="0.2.0" />
802
+ <skip_special_tokens value="True" />
803
+ <streaming_detokenizer value="False" />
804
+ <tiktoken_version value="0.8.0" />
805
+ <tokenizer_output_type value="i64" />
806
+ <tokenizers_version value="0.20.3" />
807
+ <transformers_version value="4.46.1" />
808
+ <use_max_padding value="False" />
809
+ <use_sentencepiece_backend value="False" />
810
+ <utf8_replace_mode value="replace" />
811
+ <with_detokenizer value="True" />
812
+ </rt_info>
813
+ </net>