sgao42 commited on
Commit
aaa5dc5
·
verified ·
1 Parent(s): c5bf45f

Upload 2 files

Browse files
tokenizer/openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4881bedb5628bac0d292f031cfa4d99bf9260353b85d0d8b284c28cdd38d8b29
3
+ size 616767
tokenizer/openvino_detokenizer.xml ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_128" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_128">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_154" type="Convert" version="opset1">
14
+ <data destination_type="i32" />
15
+ <input>
16
+ <port id="0" precision="I64">
17
+ <dim>-1</dim>
18
+ <dim>-1</dim>
19
+ </port>
20
+ </input>
21
+ <output>
22
+ <port id="1" precision="I32">
23
+ <dim>-1</dim>
24
+ <dim>-1</dim>
25
+ </port>
26
+ </output>
27
+ </layer>
28
+ <layer id="2" name="Constant_92" type="Const" version="opset1">
29
+ <data element_type="u8" shape="616710" offset="0" size="616710" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>616710</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_93" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>616710</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I32">
45
+ <dim>-1</dim>
46
+ </port>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="U8">
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="VocabDecoder_129" type="VocabDecoder" version="extension">
56
+ <data skip_tokens="49406, 49407" />
57
+ <input>
58
+ <port id="0" precision="I32">
59
+ <dim>-1</dim>
60
+ <dim>-1</dim>
61
+ </port>
62
+ <port id="1" precision="I32">
63
+ <dim>-1</dim>
64
+ </port>
65
+ <port id="2" precision="I32">
66
+ <dim>-1</dim>
67
+ </port>
68
+ <port id="3" precision="U8">
69
+ <dim>-1</dim>
70
+ </port>
71
+ </input>
72
+ <output>
73
+ <port id="4" precision="I32">
74
+ <dim>-1</dim>
75
+ </port>
76
+ <port id="5" precision="I32">
77
+ <dim>-1</dim>
78
+ </port>
79
+ <port id="6" precision="I32">
80
+ <dim>-1</dim>
81
+ </port>
82
+ <port id="7" precision="I32">
83
+ <dim>-1</dim>
84
+ </port>
85
+ <port id="8" precision="U8">
86
+ <dim>-1</dim>
87
+ </port>
88
+ </output>
89
+ </layer>
90
+ <layer id="5" name="FuzeRagged_130" type="FuzeRagged" version="extension">
91
+ <input>
92
+ <port id="0" precision="I32">
93
+ <dim>-1</dim>
94
+ </port>
95
+ <port id="1" precision="I32">
96
+ <dim>-1</dim>
97
+ </port>
98
+ <port id="2" precision="I32">
99
+ <dim>-1</dim>
100
+ </port>
101
+ <port id="3" precision="I32">
102
+ <dim>-1</dim>
103
+ </port>
104
+ </input>
105
+ <output>
106
+ <port id="4" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="5" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="6" name="Constant_132" type="Const" version="opset1">
115
+ <data element_type="u8" shape="4" offset="616710" size="4" />
116
+ <output>
117
+ <port id="0" precision="U8">
118
+ <dim>4</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="7" name="Constant_134" type="Const" version="opset1">
123
+ <data element_type="u8" shape="1" offset="616714" size="1" />
124
+ <output>
125
+ <port id="0" precision="U8">
126
+ <dim>1</dim>
127
+ </port>
128
+ </output>
129
+ </layer>
130
+ <layer id="8" name="RegexNormalization_135" type="RegexNormalization" version="extension">
131
+ <data global_replace="true" />
132
+ <input>
133
+ <port id="0" precision="I32">
134
+ <dim>-1</dim>
135
+ </port>
136
+ <port id="1" precision="I32">
137
+ <dim>-1</dim>
138
+ </port>
139
+ <port id="2" precision="U8">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="3" precision="U8">
143
+ <dim>4</dim>
144
+ </port>
145
+ <port id="4" precision="U8">
146
+ <dim>1</dim>
147
+ </port>
148
+ </input>
149
+ <output>
150
+ <port id="5" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="6" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="7" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ </output>
160
+ </layer>
161
+ <layer id="9" name="Constant_137" type="Const" version="opset1">
162
+ <data element_type="u8" shape="2" offset="616715" size="2" />
163
+ <output>
164
+ <port id="0" precision="U8">
165
+ <dim>2</dim>
166
+ </port>
167
+ </output>
168
+ </layer>
169
+ <layer id="10" name="Constant_139" type="Const" version="opset1">
170
+ <data element_type="u8" shape="0" offset="616717" size="1" />
171
+ <output>
172
+ <port id="0" precision="U8">
173
+ <dim>0</dim>
174
+ </port>
175
+ </output>
176
+ </layer>
177
+ <layer id="11" name="RegexNormalization_140" type="RegexNormalization" version="extension">
178
+ <data global_replace="true" />
179
+ <input>
180
+ <port id="0" precision="I32">
181
+ <dim>-1</dim>
182
+ </port>
183
+ <port id="1" precision="I32">
184
+ <dim>-1</dim>
185
+ </port>
186
+ <port id="2" precision="U8">
187
+ <dim>-1</dim>
188
+ </port>
189
+ <port id="3" precision="U8">
190
+ <dim>2</dim>
191
+ </port>
192
+ <port id="4" precision="U8">
193
+ <dim>0</dim>
194
+ </port>
195
+ </input>
196
+ <output>
197
+ <port id="5" precision="I32">
198
+ <dim>-1</dim>
199
+ </port>
200
+ <port id="6" precision="I32">
201
+ <dim>-1</dim>
202
+ </port>
203
+ <port id="7" precision="U8">
204
+ <dim>-1</dim>
205
+ </port>
206
+ </output>
207
+ </layer>
208
+ <layer id="12" name="Constant_142" type="Const" version="opset1">
209
+ <data element_type="u8" shape="47" offset="616718" size="47" />
210
+ <output>
211
+ <port id="0" precision="U8">
212
+ <dim>47</dim>
213
+ </port>
214
+ </output>
215
+ </layer>
216
+ <layer id="13" name="Constant_144" type="Const" version="opset1">
217
+ <data element_type="u8" shape="2" offset="616765" size="2" />
218
+ <output>
219
+ <port id="0" precision="U8">
220
+ <dim>2</dim>
221
+ </port>
222
+ </output>
223
+ </layer>
224
+ <layer id="14" name="RegexNormalization_145" type="RegexNormalization" version="extension">
225
+ <data global_replace="true" />
226
+ <input>
227
+ <port id="0" precision="I32">
228
+ <dim>-1</dim>
229
+ </port>
230
+ <port id="1" precision="I32">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="2" precision="U8">
234
+ <dim>-1</dim>
235
+ </port>
236
+ <port id="3" precision="U8">
237
+ <dim>47</dim>
238
+ </port>
239
+ <port id="4" precision="U8">
240
+ <dim>2</dim>
241
+ </port>
242
+ </input>
243
+ <output>
244
+ <port id="5" precision="I32">
245
+ <dim>-1</dim>
246
+ </port>
247
+ <port id="6" precision="I32">
248
+ <dim>-1</dim>
249
+ </port>
250
+ <port id="7" precision="U8">
251
+ <dim>-1</dim>
252
+ </port>
253
+ </output>
254
+ </layer>
255
+ <layer id="15" name="StringTensorPack_146" type="StringTensorPack" version="extension">
256
+ <data mode="begins_ends" />
257
+ <input>
258
+ <port id="0" precision="I32">
259
+ <dim>-1</dim>
260
+ </port>
261
+ <port id="1" precision="I32">
262
+ <dim>-1</dim>
263
+ </port>
264
+ <port id="2" precision="U8">
265
+ <dim>-1</dim>
266
+ </port>
267
+ </input>
268
+ <output>
269
+ <port id="3" precision="STRING" names="string_output">
270
+ <dim>-1</dim>
271
+ </port>
272
+ </output>
273
+ </layer>
274
+ <layer id="16" name="Result_147" type="Result" version="opset1">
275
+ <input>
276
+ <port id="0" precision="STRING">
277
+ <dim>-1</dim>
278
+ </port>
279
+ </input>
280
+ </layer>
281
+ </layers>
282
+ <edges>
283
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
284
+ <edge from-layer="1" from-port="1" to-layer="4" to-port="0" />
285
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
286
+ <edge from-layer="3" from-port="1" to-layer="4" to-port="1" />
287
+ <edge from-layer="3" from-port="2" to-layer="4" to-port="2" />
288
+ <edge from-layer="3" from-port="3" to-layer="4" to-port="3" />
289
+ <edge from-layer="4" from-port="4" to-layer="5" to-port="0" />
290
+ <edge from-layer="4" from-port="5" to-layer="5" to-port="1" />
291
+ <edge from-layer="4" from-port="6" to-layer="5" to-port="2" />
292
+ <edge from-layer="4" from-port="7" to-layer="5" to-port="3" />
293
+ <edge from-layer="4" from-port="8" to-layer="8" to-port="2" />
294
+ <edge from-layer="5" from-port="4" to-layer="8" to-port="0" />
295
+ <edge from-layer="5" from-port="5" to-layer="8" to-port="1" />
296
+ <edge from-layer="6" from-port="0" to-layer="8" to-port="3" />
297
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="4" />
298
+ <edge from-layer="8" from-port="5" to-layer="11" to-port="0" />
299
+ <edge from-layer="8" from-port="6" to-layer="11" to-port="1" />
300
+ <edge from-layer="8" from-port="7" to-layer="11" to-port="2" />
301
+ <edge from-layer="9" from-port="0" to-layer="11" to-port="3" />
302
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="4" />
303
+ <edge from-layer="11" from-port="5" to-layer="14" to-port="0" />
304
+ <edge from-layer="11" from-port="6" to-layer="14" to-port="1" />
305
+ <edge from-layer="11" from-port="7" to-layer="14" to-port="2" />
306
+ <edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
307
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
308
+ <edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
309
+ <edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
310
+ <edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
311
+ <edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
312
+ </edges>
313
+ <rt_info>
314
+ <add_attention_mask value="True" />
315
+ <add_prefix_space />
316
+ <add_special_tokens value="True" />
317
+ <bos_token_id value="49406" />
318
+ <clean_up_tokenization_spaces />
319
+ <detokenizer_input_type value="i64" />
320
+ <eos_token_id value="49407" />
321
+ <handle_special_tokens_with_re />
322
+ <number_of_inputs value="1" />
323
+ <openvino_tokenizers_version value="2024.5.0.0" />
324
+ <openvino_version value="2024.5.0" />
325
+ <original_tokenizer_class value="&lt;class 'transformers.models.clip.tokenization_clip_fast.CLIPTokenizerFast'>" />
326
+ <pad_token_id value="49407" />
327
+ <sentencepiece_version value="0.2.0" />
328
+ <skip_special_tokens value="True" />
329
+ <streaming_detokenizer value="False" />
330
+ <tiktoken_version value="0.7.0" />
331
+ <tokenizer_output_type value="i64" />
332
+ <tokenizers_version value="0.19.1" />
333
+ <transformers_version value="4.44.2" />
334
+ <use_max_padding value="False" />
335
+ <use_sentencepiece_backend value="False" />
336
+ <utf8_replace_mode />
337
+ <with_detokenizer value="True" />
338
+ </rt_info>
339
+ </net>