Hugging Face's logo

santhosh
/
multilingual-e5-base-int8-ov

Sentence Similarity
sentence-transformers
OpenVINO
xlm-roberta
mteb
Sentence Transformers
Eval Results
text-embeddings-inference
Model card Files
xet
Community
santhosh commited on
Commit
03a7d01
·
verified ·
1 Parent(s): 59425b9

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +27 -0
  3. openvino_detokenizer.bin +3 -0
  4. openvino_detokenizer.xml +325 -0
  5. openvino_model.bin +3 -0
  6. openvino_model.xml +0 -0
  7. openvino_tokenizer.bin +3 -0
  8. openvino_tokenizer.xml +867 -0
  9. sentencepiece.bpe.model +3 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +55 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.53.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a016273ee13b5debc5467f3215863b70ef698453ee3343087658fd09a85eec50
3
+ size 4272179
openvino_detokenizer.xml ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_12095" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_12095">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_12295" 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_12097" type="Const" version="opset1">
29
+ <data element_type="i32" shape="250002" offset="0" size="1000008" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>250002</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_12099" type="Const" version="opset1">
37
+ <data element_type="i32" shape="250002" offset="1000008" size="1000008" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>250002</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_12101" type="Const" version="opset1">
45
+ <data element_type="u8" shape="2272087" offset="2000016" size="2272087" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>2272087</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_12106" type="Const" version="opset1">
53
+ <data element_type="i32" shape="5" offset="4272103" size="20" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>5</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_12108" type="VocabDecoder" version="extension">
61
+ <data skip_tokens="" />
62
+ <input>
63
+ <port id="0" precision="I32">
64
+ <dim>-1</dim>
65
+ <dim>-1</dim>
66
+ </port>
67
+ <port id="1" precision="I32">
68
+ <dim>250002</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>250002</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>2272087</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>5</dim>
78
+ </port>
79
+ </input>
80
+ <output>
81
+ <port id="5" precision="I32">
82
+ <dim>-1</dim>
83
+ </port>
84
+ <port id="6" precision="I32">
85
+ <dim>-1</dim>
86
+ </port>
87
+ <port id="7" precision="I32">
88
+ <dim>-1</dim>
89
+ </port>
90
+ <port id="8" precision="I32">
91
+ <dim>-1</dim>
92
+ </port>
93
+ <port id="9" precision="U8">
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="FuzeRagged_12109" type="FuzeRagged" version="extension">
99
+ <input>
100
+ <port id="0" precision="I32">
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I32">
104
+ <dim>-1</dim>
105
+ </port>
106
+ <port id="2" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="4" precision="I32">
115
+ <dim>-1</dim>
116
+ </port>
117
+ <port id="5" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="8" name="Constant_12111" type="Const" version="opset1">
123
+ <data element_type="u8" shape="2" offset="4272123" size="2" />
124
+ <output>
125
+ <port id="0" precision="U8">
126
+ <dim>2</dim>
127
+ </port>
128
+ </output>
129
+ </layer>
130
+ <layer id="9" name="Constant_12113" type="Const" version="opset1">
131
+ <data element_type="u8" shape="0" offset="4272125" size="1" />
132
+ <output>
133
+ <port id="0" precision="U8">
134
+ <dim>0</dim>
135
+ </port>
136
+ </output>
137
+ </layer>
138
+ <layer id="10" name="RegexNormalization_12114" type="RegexNormalization" version="extension">
139
+ <data global_replace="true" />
140
+ <input>
141
+ <port id="0" precision="I32">
142
+ <dim>-1</dim>
143
+ </port>
144
+ <port id="1" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="2" precision="U8">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="3" precision="U8">
151
+ <dim>2</dim>
152
+ </port>
153
+ <port id="4" precision="U8">
154
+ <dim>0</dim>
155
+ </port>
156
+ </input>
157
+ <output>
158
+ <port id="5" precision="I32">
159
+ <dim>-1</dim>
160
+ </port>
161
+ <port id="6" precision="I32">
162
+ <dim>-1</dim>
163
+ </port>
164
+ <port id="7" precision="U8">
165
+ <dim>-1</dim>
166
+ </port>
167
+ </output>
168
+ </layer>
169
+ <layer id="11" name="UTF8Validate_12115" type="UTF8Validate" version="extension">
170
+ <data replace_mode="true" />
171
+ <input>
172
+ <port id="0" precision="I32">
173
+ <dim>-1</dim>
174
+ </port>
175
+ <port id="1" precision="I32">
176
+ <dim>-1</dim>
177
+ </port>
178
+ <port id="2" precision="U8">
179
+ <dim>-1</dim>
180
+ </port>
181
+ </input>
182
+ <output>
183
+ <port id="3" precision="I32">
184
+ <dim>-1</dim>
185
+ </port>
186
+ <port id="4" precision="I32">
187
+ <dim>-1</dim>
188
+ </port>
189
+ <port id="5" precision="U8">
190
+ <dim>-1</dim>
191
+ </port>
192
+ </output>
193
+ </layer>
194
+ <layer id="12" name="Constant_12117" type="Const" version="opset1">
195
+ <data element_type="u8" shape="51" offset="4272126" size="51" />
196
+ <output>
197
+ <port id="0" precision="U8">
198
+ <dim>51</dim>
199
+ </port>
200
+ </output>
201
+ </layer>
202
+ <layer id="13" name="Constant_12119" type="Const" version="opset1">
203
+ <data element_type="u8" shape="2" offset="4272177" size="2" />
204
+ <output>
205
+ <port id="0" precision="U8">
206
+ <dim>2</dim>
207
+ </port>
208
+ </output>
209
+ </layer>
210
+ <layer id="14" name="RegexNormalization_12120" type="RegexNormalization" version="extension">
211
+ <data global_replace="true" />
212
+ <input>
213
+ <port id="0" precision="I32">
214
+ <dim>-1</dim>
215
+ </port>
216
+ <port id="1" precision="I32">
217
+ <dim>-1</dim>
218
+ </port>
219
+ <port id="2" precision="U8">
220
+ <dim>-1</dim>
221
+ </port>
222
+ <port id="3" precision="U8">
223
+ <dim>51</dim>
224
+ </port>
225
+ <port id="4" precision="U8">
226
+ <dim>2</dim>
227
+ </port>
228
+ </input>
229
+ <output>
230
+ <port id="5" precision="I32">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="6" precision="I32">
234
+ <dim>-1</dim>
235
+ </port>
236
+ <port id="7" precision="U8">
237
+ <dim>-1</dim>
238
+ </port>
239
+ </output>
240
+ </layer>
241
+ <layer id="15" name="StringTensorPack_12121" type="StringTensorPack" version="opset15">
242
+ <input>
243
+ <port id="0" precision="I32">
244
+ <dim>-1</dim>
245
+ </port>
246
+ <port id="1" precision="I32">
247
+ <dim>-1</dim>
248
+ </port>
249
+ <port id="2" precision="U8">
250
+ <dim>-1</dim>
251
+ </port>
252
+ </input>
253
+ <output>
254
+ <port id="3" precision="STRING" names="Result_12122,string_output">
255
+ <dim>-1</dim>
256
+ </port>
257
+ </output>
258
+ </layer>
259
+ <layer id="16" name="Result_12122" type="Result" version="opset1" output_names="Result_12122,string_output">
260
+ <input>
261
+ <port id="0" precision="STRING">
262
+ <dim>-1</dim>
263
+ </port>
264
+ </input>
265
+ </layer>
266
+ </layers>
267
+ <edges>
268
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
269
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
270
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
271
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
272
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
273
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
274
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
275
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
276
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
277
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
278
+ <edge from-layer="6" from-port="9" to-layer="10" to-port="2" />
279
+ <edge from-layer="7" from-port="4" to-layer="10" to-port="0" />
280
+ <edge from-layer="7" from-port="5" to-layer="10" to-port="1" />
281
+ <edge from-layer="8" from-port="0" to-layer="10" to-port="3" />
282
+ <edge from-layer="9" from-port="0" to-layer="10" to-port="4" />
283
+ <edge from-layer="10" from-port="5" to-layer="11" to-port="0" />
284
+ <edge from-layer="10" from-port="6" to-layer="11" to-port="1" />
285
+ <edge from-layer="10" from-port="7" to-layer="11" to-port="2" />
286
+ <edge from-layer="11" from-port="3" to-layer="14" to-port="0" />
287
+ <edge from-layer="11" from-port="4" to-layer="14" to-port="1" />
288
+ <edge from-layer="11" from-port="5" to-layer="14" to-port="2" />
289
+ <edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
290
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
291
+ <edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
292
+ <edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
293
+ <edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
294
+ <edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
295
+ </edges>
296
+ <rt_info>
297
+ <add_attention_mask value="True" />
298
+ <add_prefix_space />
299
+ <add_special_tokens value="True" />
300
+ <bos_token_id value="0" />
301
+ <clean_up_tokenization_spaces />
302
+ <detokenizer_input_type value="i64" />
303
+ <eos_token_id value="2" />
304
+ <handle_special_tokens_with_re />
305
+ <max_length />
306
+ <number_of_inputs value="1" />
307
+ <openvino_tokenizers_version value="2025.2.0.1-567-7885335c24b" />
308
+ <openvino_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
309
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}], &quot;special_tokens&quot;: {&quot;&lt;/s>&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;ids&quot;: [2], &quot;tokens&quot;: [&quot;&lt;/s>&quot;]}, &quot;&lt;s>&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;ids&quot;: [0], &quot;tokens&quot;: [&quot;&lt;s>&quot;]}}}" />
310
+ <original_tokenizer_class value="&lt;class 'transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast'>" />
311
+ <pad_token_id value="1" />
312
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [0, -1, 2], &quot;type_ids&quot;: [0, 0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [0, -1, 2, 2, -2, 2], &quot;type_ids&quot;: [0, 0, 0, 0, 0, 0]}}" />
313
+ <sentencepiece_version value="0.2.1" />
314
+ <skip_special_tokens value="True" />
315
+ <streaming_detokenizer value="False" />
316
+ <tiktoken_version value="0.11.0" />
317
+ <tokenizer_output_type value="i64" />
318
+ <tokenizers_version value="0.21.4" />
319
+ <transformers_version value="4.53.3" />
320
+ <use_max_padding value="False" />
321
+ <use_sentencepiece_backend value="False" />
322
+ <utf8_replace_mode value="replace" />
323
+ <with_detokenizer value="True" />
324
+ </rt_info>
325
+ </net>
openvino_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d05d97cd7a6c617b5222d2a1719108c7c0756c308eeb9ab9641adaebb2ce54
3
+ size 278821743
openvino_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31b2a4ca80867d8fc6a0537498b4787dfae1f152460beef061ad0377b794bb2
3
+ size 5319041
openvino_tokenizer.xml ADDED
@@ -0,0 +1,867 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_11970" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_11970">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_12076" 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_12077" 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_12078" type="Const" version="opset1">
25
+ <data element_type="i32" shape="1" offset="0" 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_11976" type="Const" version="opset1">
33
+ <data element_type="i64" shape="" offset="8" size="8" />
34
+ <output>
35
+ <port id="0" precision="I64" />
36
+ </output>
37
+ </layer>
38
+ <layer id="5" name="StringTensorUnpack_11971" type="StringTensorUnpack" version="opset15">
39
+ <input>
40
+ <port id="0" precision="STRING">
41
+ <dim>-1</dim>
42
+ </port>
43
+ </input>
44
+ <output>
45
+ <port id="1" precision="I32">
46
+ <dim>-1</dim>
47
+ </port>
48
+ <port id="2" precision="I32">
49
+ <dim>-1</dim>
50
+ </port>
51
+ <port id="3" precision="U8">
52
+ <dim>-1</dim>
53
+ </port>
54
+ </output>
55
+ </layer>
56
+ <layer id="6" name="ShapeOf_11972" type="ShapeOf" version="opset3">
57
+ <data output_type="i64" />
58
+ <input>
59
+ <port id="0" precision="I32">
60
+ <dim>-1</dim>
61
+ </port>
62
+ </input>
63
+ <output>
64
+ <port id="1" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ </output>
68
+ </layer>
69
+ <layer id="7" name="Constant_11973" type="Const" version="opset1">
70
+ <data element_type="i64" shape="" offset="8" size="8" />
71
+ <output>
72
+ <port id="0" precision="I64" />
73
+ </output>
74
+ </layer>
75
+ <layer id="8" name="Constant_11974" type="Const" version="opset1">
76
+ <data element_type="i64" shape="" offset="8" size="8" />
77
+ <output>
78
+ <port id="0" precision="I64" />
79
+ </output>
80
+ </layer>
81
+ <layer id="9" name="Gather_11975" type="Gather" version="opset8">
82
+ <data batch_dims="0" />
83
+ <input>
84
+ <port id="0" precision="I64">
85
+ <dim>1</dim>
86
+ </port>
87
+ <port id="1" precision="I64" />
88
+ <port id="2" precision="I64" />
89
+ </input>
90
+ <output>
91
+ <port id="3" precision="I64" />
92
+ </output>
93
+ </layer>
94
+ <layer id="10" name="Constant_11977" type="Const" version="opset1">
95
+ <data element_type="i64" shape="" offset="16" size="8" />
96
+ <output>
97
+ <port id="0" precision="I64" />
98
+ </output>
99
+ </layer>
100
+ <layer id="11" name="Range_11978" type="Range" version="opset4">
101
+ <data output_type="i32" />
102
+ <input>
103
+ <port id="0" precision="I64" />
104
+ <port id="1" precision="I64" />
105
+ <port id="2" precision="I64" />
106
+ </input>
107
+ <output>
108
+ <port id="3" precision="I32">
109
+ <dim>-1</dim>
110
+ </port>
111
+ </output>
112
+ </layer>
113
+ <layer id="12" name="Constant_11979" type="Const" version="opset1">
114
+ <data element_type="i64" shape="" offset="16" size="8" />
115
+ <output>
116
+ <port id="0" precision="I64" />
117
+ </output>
118
+ </layer>
119
+ <layer id="13" name="Constant_11980" type="Const" version="opset1">
120
+ <data element_type="i64" shape="" offset="16" size="8" />
121
+ <output>
122
+ <port id="0" precision="I64" />
123
+ </output>
124
+ </layer>
125
+ <layer id="14" name="Add_11981" type="Add" version="opset1">
126
+ <data auto_broadcast="numpy" />
127
+ <input>
128
+ <port id="0" precision="I64" />
129
+ <port id="1" precision="I64" />
130
+ </input>
131
+ <output>
132
+ <port id="2" precision="I64" />
133
+ </output>
134
+ </layer>
135
+ <layer id="15" name="Constant_11982" type="Const" version="opset1">
136
+ <data element_type="i64" shape="" offset="16" size="8" />
137
+ <output>
138
+ <port id="0" precision="I64" />
139
+ </output>
140
+ </layer>
141
+ <layer id="16" name="Range_11983" type="Range" version="opset4">
142
+ <data output_type="i32" />
143
+ <input>
144
+ <port id="0" precision="I64" />
145
+ <port id="1" precision="I64" />
146
+ <port id="2" precision="I64" />
147
+ </input>
148
+ <output>
149
+ <port id="3" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ </output>
153
+ </layer>
154
+ <layer id="17" name="Constant_12045" type="Const" version="opset1">
155
+ <data element_type="u8" shape="55" offset="24" size="55" />
156
+ <output>
157
+ <port id="0" precision="U8">
158
+ <dim>55</dim>
159
+ </port>
160
+ </output>
161
+ </layer>
162
+ <layer id="18" name="SpecialTokensSplit_12046" type="SpecialTokensSplit" version="extension">
163
+ <input>
164
+ <port id="0" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="1" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="2" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="3" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="4" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="5" precision="U8">
180
+ <dim>55</dim>
181
+ </port>
182
+ </input>
183
+ <output>
184
+ <port id="6" precision="I32">
185
+ <dim>-1</dim>
186
+ </port>
187
+ <port id="7" precision="I32">
188
+ <dim>-1</dim>
189
+ </port>
190
+ <port id="8" precision="I32">
191
+ <dim>-1</dim>
192
+ </port>
193
+ <port id="9" precision="I32">
194
+ <dim>-1</dim>
195
+ </port>
196
+ <port id="10" precision="U8">
197
+ <dim>-1</dim>
198
+ </port>
199
+ <port id="11" precision="BOOL">
200
+ <dim>-1</dim>
201
+ </port>
202
+ </output>
203
+ </layer>
204
+ <layer id="19" name="Constant_12047" type="Const" version="opset1">
205
+ <data element_type="u8" shape="237539" offset="79" size="237539" />
206
+ <output>
207
+ <port id="0" precision="U8">
208
+ <dim>237539</dim>
209
+ </port>
210
+ </output>
211
+ </layer>
212
+ <layer id="20" name="CharsMapNormalization_12048" type="CharsMapNormalization" version="extension">
213
+ <data add_dummy_prefix="false" remove_extra_whitespaces="true" escape_whitespaces="false" normalization_form="" case_fold="false" nmt="false" />
214
+ <input>
215
+ <port id="0" precision="I32">
216
+ <dim>-1</dim>
217
+ </port>
218
+ <port id="1" precision="I32">
219
+ <dim>-1</dim>
220
+ </port>
221
+ <port id="2" precision="U8">
222
+ <dim>-1</dim>
223
+ </port>
224
+ <port id="3" precision="BOOL">
225
+ <dim>-1</dim>
226
+ </port>
227
+ <port id="4" precision="U8">
228
+ <dim>237539</dim>
229
+ </port>
230
+ </input>
231
+ <output>
232
+ <port id="5" precision="I32">
233
+ <dim>-1</dim>
234
+ </port>
235
+ <port id="6" precision="I32">
236
+ <dim>-1</dim>
237
+ </port>
238
+ <port id="7" precision="U8">
239
+ <dim>-1</dim>
240
+ </port>
241
+ <port id="8" precision="BOOL">
242
+ <dim>-1</dim>
243
+ </port>
244
+ </output>
245
+ </layer>
246
+ <layer id="21" name="Constant_12050" type="Const" version="opset1">
247
+ <data element_type="u8" shape="1" offset="237618" size="1" />
248
+ <output>
249
+ <port id="0" precision="U8">
250
+ <dim>1</dim>
251
+ </port>
252
+ </output>
253
+ </layer>
254
+ <layer id="22" name="Constant_12052" type="Const" version="opset1">
255
+ <data element_type="u8" shape="3" offset="237619" size="3" />
256
+ <output>
257
+ <port id="0" precision="U8">
258
+ <dim>3</dim>
259
+ </port>
260
+ </output>
261
+ </layer>
262
+ <layer id="23" name="RegexNormalization_12053" type="RegexNormalization" version="extension">
263
+ <data global_replace="true" />
264
+ <input>
265
+ <port id="0" precision="I32">
266
+ <dim>-1</dim>
267
+ </port>
268
+ <port id="1" precision="I32">
269
+ <dim>-1</dim>
270
+ </port>
271
+ <port id="2" precision="U8">
272
+ <dim>-1</dim>
273
+ </port>
274
+ <port id="3" precision="BOOL">
275
+ <dim>-1</dim>
276
+ </port>
277
+ <port id="4" precision="U8">
278
+ <dim>1</dim>
279
+ </port>
280
+ <port id="5" precision="U8">
281
+ <dim>3</dim>
282
+ </port>
283
+ </input>
284
+ <output>
285
+ <port id="6" precision="I32">
286
+ <dim>-1</dim>
287
+ </port>
288
+ <port id="7" precision="I32">
289
+ <dim>-1</dim>
290
+ </port>
291
+ <port id="8" precision="U8">
292
+ <dim>-1</dim>
293
+ </port>
294
+ <port id="9" precision="BOOL">
295
+ <dim>-1</dim>
296
+ </port>
297
+ </output>
298
+ </layer>
299
+ <layer id="24" name="Constant_12055" type="Const" version="opset1">
300
+ <data element_type="u8" shape="11" offset="237622" size="11" />
301
+ <output>
302
+ <port id="0" precision="U8">
303
+ <dim>11</dim>
304
+ </port>
305
+ </output>
306
+ </layer>
307
+ <layer id="25" name="Constant_12057" type="Const" version="opset1">
308
+ <data element_type="u8" shape="5" offset="237633" size="5" />
309
+ <output>
310
+ <port id="0" precision="U8">
311
+ <dim>5</dim>
312
+ </port>
313
+ </output>
314
+ </layer>
315
+ <layer id="26" name="RegexNormalization_12058" type="RegexNormalization" version="extension">
316
+ <data global_replace="true" />
317
+ <input>
318
+ <port id="0" precision="I32">
319
+ <dim>-1</dim>
320
+ </port>
321
+ <port id="1" precision="I32">
322
+ <dim>-1</dim>
323
+ </port>
324
+ <port id="2" precision="U8">
325
+ <dim>-1</dim>
326
+ </port>
327
+ <port id="3" precision="BOOL">
328
+ <dim>-1</dim>
329
+ </port>
330
+ <port id="4" precision="U8">
331
+ <dim>11</dim>
332
+ </port>
333
+ <port id="5" precision="U8">
334
+ <dim>5</dim>
335
+ </port>
336
+ </input>
337
+ <output>
338
+ <port id="6" precision="I32">
339
+ <dim>-1</dim>
340
+ </port>
341
+ <port id="7" precision="I32">
342
+ <dim>-1</dim>
343
+ </port>
344
+ <port id="8" precision="U8">
345
+ <dim>-1</dim>
346
+ </port>
347
+ <port id="9" precision="BOOL">
348
+ <dim>-1</dim>
349
+ </port>
350
+ </output>
351
+ </layer>
352
+ <layer id="27" name="Constant_12060" type="Const" version="opset1">
353
+ <data element_type="u8" shape="3" offset="237619" size="3" />
354
+ <output>
355
+ <port id="0" precision="U8">
356
+ <dim>3</dim>
357
+ </port>
358
+ </output>
359
+ </layer>
360
+ <layer id="28" name="RegexSplit_12061" type="RegexSplit" version="extension">
361
+ <data behaviour="mergedwithnext" invert="false" max_splits="-1" />
362
+ <input>
363
+ <port id="0" precision="I32">
364
+ <dim>-1</dim>
365
+ </port>
366
+ <port id="1" precision="I32">
367
+ <dim>-1</dim>
368
+ </port>
369
+ <port id="2" precision="I32">
370
+ <dim>-1</dim>
371
+ </port>
372
+ <port id="3" precision="I32">
373
+ <dim>-1</dim>
374
+ </port>
375
+ <port id="4" precision="U8">
376
+ <dim>-1</dim>
377
+ </port>
378
+ <port id="5" precision="BOOL">
379
+ <dim>-1</dim>
380
+ </port>
381
+ <port id="6" precision="U8">
382
+ <dim>3</dim>
383
+ </port>
384
+ </input>
385
+ <output>
386
+ <port id="7" precision="I32">
387
+ <dim>-1</dim>
388
+ </port>
389
+ <port id="8" precision="I32">
390
+ <dim>-1</dim>
391
+ </port>
392
+ <port id="9" precision="I32">
393
+ <dim>-1</dim>
394
+ </port>
395
+ <port id="10" precision="I32">
396
+ <dim>-1</dim>
397
+ </port>
398
+ <port id="11" precision="U8">
399
+ <dim>-1</dim>
400
+ </port>
401
+ <port id="12" precision="BOOL">
402
+ <dim>-1</dim>
403
+ </port>
404
+ </output>
405
+ </layer>
406
+ <layer id="29" name="Constant_12063" type="Const" version="opset1">
407
+ <data element_type="i32" shape="250002" offset="237638" size="1000008" />
408
+ <output>
409
+ <port id="0" precision="I32">
410
+ <dim>250002</dim>
411
+ </port>
412
+ </output>
413
+ </layer>
414
+ <layer id="30" name="Constant_12065" type="Const" version="opset1">
415
+ <data element_type="i32" shape="250002" offset="1237646" size="1000008" />
416
+ <output>
417
+ <port id="0" precision="I32">
418
+ <dim>250002</dim>
419
+ </port>
420
+ </output>
421
+ </layer>
422
+ <layer id="31" name="Constant_12067" type="Const" version="opset1">
423
+ <data element_type="u8" shape="2581345" offset="2237654" size="2581345" />
424
+ <output>
425
+ <port id="0" precision="U8">
426
+ <dim>2581345</dim>
427
+ </port>
428
+ </output>
429
+ </layer>
430
+ <layer id="32" name="Constant_12068_compressed" type="Const" version="opset1">
431
+ <data element_type="f16" shape="250002" offset="4818999" size="500004" />
432
+ <output>
433
+ <port id="0" precision="FP16">
434
+ <dim>250002</dim>
435
+ </port>
436
+ </output>
437
+ </layer>
438
+ <layer id="33" name="Constant_12068" type="Convert" version="opset1">
439
+ <data destination_type="f32" />
440
+ <rt_info>
441
+ <attribute name="decompression" version="0" />
442
+ </rt_info>
443
+ <input>
444
+ <port id="0" precision="FP16">
445
+ <dim>250002</dim>
446
+ </port>
447
+ </input>
448
+ <output>
449
+ <port id="1" precision="FP32">
450
+ <dim>250002</dim>
451
+ </port>
452
+ </output>
453
+ </layer>
454
+ <layer id="34" name="UnigramTokenizer_12069" type="UnigramTokenizer" version="extension">
455
+ <data byte_fallback="false" unk_token_id="3" fuse_unk="true" min_score="inf" />
456
+ <input>
457
+ <port id="0" precision="I32">
458
+ <dim>-1</dim>
459
+ </port>
460
+ <port id="1" precision="I32">
461
+ <dim>-1</dim>
462
+ </port>
463
+ <port id="2" precision="I32">
464
+ <dim>-1</dim>
465
+ </port>
466
+ <port id="3" precision="I32">
467
+ <dim>-1</dim>
468
+ </port>
469
+ <port id="4" precision="U8">
470
+ <dim>-1</dim>
471
+ </port>
472
+ <port id="5" precision="I32">
473
+ <dim>250002</dim>
474
+ </port>
475
+ <port id="6" precision="I32">
476
+ <dim>250002</dim>
477
+ </port>
478
+ <port id="7" precision="U8">
479
+ <dim>2581345</dim>
480
+ </port>
481
+ <port id="8" precision="FP32">
482
+ <dim>250002</dim>
483
+ </port>
484
+ </input>
485
+ <output>
486
+ <port id="9" precision="I32">
487
+ <dim>-1</dim>
488
+ </port>
489
+ <port id="10" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="11" precision="I32">
493
+ <dim>-1</dim>
494
+ </port>
495
+ </output>
496
+ </layer>
497
+ <layer id="35" name="Constant_12070" type="Const" version="opset1">
498
+ <data element_type="i32" shape="" offset="5319003" size="4" />
499
+ <output>
500
+ <port id="0" precision="I32" />
501
+ </output>
502
+ </layer>
503
+ <layer id="36" name="Constant_12072" type="Const" version="opset1">
504
+ <data element_type="u8" shape="5" offset="5319007" size="5" />
505
+ <output>
506
+ <port id="0" precision="U8">
507
+ <dim>5</dim>
508
+ </port>
509
+ </output>
510
+ </layer>
511
+ <layer id="37" name="Constant_12074" type="Const" version="opset1">
512
+ <data element_type="u8" shape="13" offset="5319012" size="13" />
513
+ <output>
514
+ <port id="0" precision="U8">
515
+ <dim>13</dim>
516
+ </port>
517
+ </output>
518
+ </layer>
519
+ <layer id="38" name="Truncate_12075" type="Truncate" version="extension">
520
+ <data m_num_inputs="1" />
521
+ <input>
522
+ <port id="0" precision="I32">
523
+ <dim>-1</dim>
524
+ </port>
525
+ <port id="1" precision="I32">
526
+ <dim>-1</dim>
527
+ </port>
528
+ <port id="2" precision="I32">
529
+ <dim>-1</dim>
530
+ </port>
531
+ <port id="3" precision="I32" />
532
+ <port id="4" precision="U8">
533
+ <dim>5</dim>
534
+ </port>
535
+ <port id="5" precision="U8">
536
+ <dim>13</dim>
537
+ </port>
538
+ </input>
539
+ <output>
540
+ <port id="6" precision="I32">
541
+ <dim>-1</dim>
542
+ </port>
543
+ <port id="7" precision="I32">
544
+ <dim>-1</dim>
545
+ </port>
546
+ <port id="8" precision="I32">
547
+ <dim>-1</dim>
548
+ </port>
549
+ </output>
550
+ </layer>
551
+ <layer id="39" name="Constant_12079" type="Const" version="opset1">
552
+ <data element_type="i32" shape="" offset="0" size="4" />
553
+ <output>
554
+ <port id="0" precision="I32" />
555
+ </output>
556
+ </layer>
557
+ <layer id="40" name="Constant_12080" type="Const" version="opset1">
558
+ <data element_type="i32" shape="" offset="4" size="4" />
559
+ <output>
560
+ <port id="0" precision="I32" />
561
+ </output>
562
+ </layer>
563
+ <layer id="41" name="Constant_12081" type="Const" version="opset1">
564
+ <data element_type="i32" shape="1" offset="5319025" size="4" />
565
+ <output>
566
+ <port id="0" precision="I32">
567
+ <dim>1</dim>
568
+ </port>
569
+ </output>
570
+ </layer>
571
+ <layer id="42" name="Constant_12082" type="Const" version="opset1">
572
+ <data element_type="i32" shape="3" offset="5319029" size="12" />
573
+ <output>
574
+ <port id="0" precision="I32">
575
+ <dim>3</dim>
576
+ </port>
577
+ </output>
578
+ </layer>
579
+ <layer id="43" name="CombineSegments_12083" type="CombineSegments" version="extension">
580
+ <input>
581
+ <port id="0" precision="I32" />
582
+ <port id="1" precision="I32" />
583
+ <port id="2" precision="I32">
584
+ <dim>1</dim>
585
+ </port>
586
+ <port id="3" precision="I32">
587
+ <dim>-1</dim>
588
+ </port>
589
+ <port id="4" precision="I32">
590
+ <dim>-1</dim>
591
+ </port>
592
+ <port id="5" precision="I32">
593
+ <dim>-1</dim>
594
+ </port>
595
+ <port id="6" precision="I32" />
596
+ <port id="7" precision="I32" />
597
+ <port id="8" precision="I32">
598
+ <dim>1</dim>
599
+ </port>
600
+ <port id="9" precision="I32">
601
+ <dim>3</dim>
602
+ </port>
603
+ </input>
604
+ <output>
605
+ <port id="10" precision="I32">
606
+ <dim>-1</dim>
607
+ </port>
608
+ <port id="11" precision="I32">
609
+ <dim>-1</dim>
610
+ </port>
611
+ <port id="12" precision="I32">
612
+ <dim>-1</dim>
613
+ </port>
614
+ <port id="13" precision="I32">
615
+ <dim>-1</dim>
616
+ </port>
617
+ <port id="14" precision="I32">
618
+ <dim>-1</dim>
619
+ </port>
620
+ <port id="15" precision="I32">
621
+ <dim>-1</dim>
622
+ </port>
623
+ </output>
624
+ </layer>
625
+ <layer id="44" name="Subtract_12084" type="Subtract" version="opset1">
626
+ <data auto_broadcast="numpy" />
627
+ <input>
628
+ <port id="0" precision="I32">
629
+ <dim>-1</dim>
630
+ </port>
631
+ <port id="1" precision="I32">
632
+ <dim>-1</dim>
633
+ </port>
634
+ </input>
635
+ <output>
636
+ <port id="2" precision="I32">
637
+ <dim>-1</dim>
638
+ </port>
639
+ </output>
640
+ </layer>
641
+ <layer id="45" name="Constant_12085" type="Const" version="opset1">
642
+ <data element_type="i32" shape="" offset="0" size="4" />
643
+ <output>
644
+ <port id="0" precision="I32" />
645
+ </output>
646
+ </layer>
647
+ <layer id="46" name="ReduceMax_12086" type="ReduceMax" version="opset1">
648
+ <data keep_dims="false" />
649
+ <input>
650
+ <port id="0" precision="I32">
651
+ <dim>-1</dim>
652
+ </port>
653
+ <port id="1" precision="I32" />
654
+ </input>
655
+ <output>
656
+ <port id="2" precision="I32" />
657
+ </output>
658
+ </layer>
659
+ <layer id="47" name="Constant_12087" type="Const" version="opset1">
660
+ <data element_type="i32" shape="" offset="4" size="4" />
661
+ <output>
662
+ <port id="0" precision="I32" />
663
+ </output>
664
+ </layer>
665
+ <layer id="48" name="RaggedToDense_12088" type="RaggedToDense" version="extension">
666
+ <data pad_right="true" m_pad_max_length="false" />
667
+ <input>
668
+ <port id="0" precision="I32">
669
+ <dim>-1</dim>
670
+ </port>
671
+ <port id="1" precision="I32">
672
+ <dim>-1</dim>
673
+ </port>
674
+ <port id="2" precision="I32">
675
+ <dim>-1</dim>
676
+ </port>
677
+ <port id="3" precision="I32" />
678
+ <port id="4" precision="I32" />
679
+ </input>
680
+ <output>
681
+ <port id="5" precision="I32">
682
+ <dim>-1</dim>
683
+ <dim>-1</dim>
684
+ </port>
685
+ <port id="6" precision="BOOL">
686
+ <dim>-1</dim>
687
+ <dim>-1</dim>
688
+ </port>
689
+ </output>
690
+ </layer>
691
+ <layer id="49" name="Convert_12089" type="Convert" version="opset1">
692
+ <data destination_type="i32" />
693
+ <input>
694
+ <port id="0" precision="BOOL">
695
+ <dim>-1</dim>
696
+ <dim>-1</dim>
697
+ </port>
698
+ </input>
699
+ <output>
700
+ <port id="1" precision="I32">
701
+ <dim>-1</dim>
702
+ <dim>-1</dim>
703
+ </port>
704
+ </output>
705
+ </layer>
706
+ <layer id="50" name="Convert_12089.0" type="Convert" version="opset1">
707
+ <data destination_type="i64" />
708
+ <input>
709
+ <port id="0" precision="I32">
710
+ <dim>-1</dim>
711
+ <dim>-1</dim>
712
+ </port>
713
+ </input>
714
+ <output>
715
+ <port id="1" precision="I64" names="attention_mask">
716
+ <dim>-1</dim>
717
+ <dim>-1</dim>
718
+ </port>
719
+ </output>
720
+ </layer>
721
+ <layer id="52" name="RaggedToDense_12088.0" type="Convert" version="opset1">
722
+ <data destination_type="i64" />
723
+ <input>
724
+ <port id="0" precision="I32">
725
+ <dim>-1</dim>
726
+ <dim>-1</dim>
727
+ </port>
728
+ </input>
729
+ <output>
730
+ <port id="1" precision="I64" names="input_ids">
731
+ <dim>-1</dim>
732
+ <dim>-1</dim>
733
+ </port>
734
+ </output>
735
+ </layer>
736
+ <layer id="53" name="Result_12092" type="Result" version="opset1" output_names="input_ids">
737
+ <input>
738
+ <port id="0" precision="I64">
739
+ <dim>-1</dim>
740
+ <dim>-1</dim>
741
+ </port>
742
+ </input>
743
+ </layer>
744
+ <layer id="51" name="Result_12094" type="Result" version="opset1" output_names="attention_mask">
745
+ <input>
746
+ <port id="0" precision="I64">
747
+ <dim>-1</dim>
748
+ <dim>-1</dim>
749
+ </port>
750
+ </input>
751
+ </layer>
752
+ </layers>
753
+ <edges>
754
+ <edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
755
+ <edge from-layer="1" from-port="0" to-layer="43" to-port="0" />
756
+ <edge from-layer="2" from-port="0" to-layer="43" to-port="1" />
757
+ <edge from-layer="3" from-port="0" to-layer="43" to-port="2" />
758
+ <edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
759
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
760
+ <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
761
+ <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
762
+ <edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
763
+ <edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
764
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
765
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
766
+ <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
767
+ <edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
768
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
769
+ <edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
770
+ <edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
771
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
772
+ <edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
773
+ <edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
774
+ <edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
775
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
776
+ <edge from-layer="18" from-port="6" to-layer="28" to-port="0" />
777
+ <edge from-layer="18" from-port="7" to-layer="28" to-port="1" />
778
+ <edge from-layer="18" from-port="11" to-layer="20" to-port="3" />
779
+ <edge from-layer="18" from-port="10" to-layer="20" to-port="2" />
780
+ <edge from-layer="18" from-port="9" to-layer="20" to-port="1" />
781
+ <edge from-layer="18" from-port="8" to-layer="20" to-port="0" />
782
+ <edge from-layer="19" from-port="0" to-layer="20" to-port="4" />
783
+ <edge from-layer="20" from-port="6" to-layer="23" to-port="1" />
784
+ <edge from-layer="20" from-port="8" to-layer="23" to-port="3" />
785
+ <edge from-layer="20" from-port="7" to-layer="23" to-port="2" />
786
+ <edge from-layer="20" from-port="5" to-layer="23" to-port="0" />
787
+ <edge from-layer="21" from-port="0" to-layer="23" to-port="4" />
788
+ <edge from-layer="22" from-port="0" to-layer="23" to-port="5" />
789
+ <edge from-layer="23" from-port="6" to-layer="26" to-port="0" />
790
+ <edge from-layer="23" from-port="7" to-layer="26" to-port="1" />
791
+ <edge from-layer="23" from-port="8" to-layer="26" to-port="2" />
792
+ <edge from-layer="23" from-port="9" to-layer="26" to-port="3" />
793
+ <edge from-layer="24" from-port="0" to-layer="26" to-port="4" />
794
+ <edge from-layer="25" from-port="0" to-layer="26" to-port="5" />
795
+ <edge from-layer="26" from-port="9" to-layer="28" to-port="5" />
796
+ <edge from-layer="26" from-port="6" to-layer="28" to-port="2" />
797
+ <edge from-layer="26" from-port="7" to-layer="28" to-port="3" />
798
+ <edge from-layer="26" from-port="8" to-layer="28" to-port="4" />
799
+ <edge from-layer="27" from-port="0" to-layer="28" to-port="6" />
800
+ <edge from-layer="28" from-port="7" to-layer="34" to-port="0" />
801
+ <edge from-layer="28" from-port="8" to-layer="34" to-port="1" />
802
+ <edge from-layer="28" from-port="9" to-layer="34" to-port="2" />
803
+ <edge from-layer="28" from-port="10" to-layer="34" to-port="3" />
804
+ <edge from-layer="28" from-port="11" to-layer="34" to-port="4" />
805
+ <edge from-layer="29" from-port="0" to-layer="34" to-port="5" />
806
+ <edge from-layer="30" from-port="0" to-layer="34" to-port="6" />
807
+ <edge from-layer="31" from-port="0" to-layer="34" to-port="7" />
808
+ <edge from-layer="32" from-port="0" to-layer="33" to-port="0" />
809
+ <edge from-layer="33" from-port="1" to-layer="34" to-port="8" />
810
+ <edge from-layer="34" from-port="9" to-layer="38" to-port="0" />
811
+ <edge from-layer="34" from-port="11" to-layer="38" to-port="2" />
812
+ <edge from-layer="34" from-port="10" to-layer="38" to-port="1" />
813
+ <edge from-layer="35" from-port="0" to-layer="38" to-port="3" />
814
+ <edge from-layer="36" from-port="0" to-layer="38" to-port="4" />
815
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="5" />
816
+ <edge from-layer="38" from-port="6" to-layer="43" to-port="3" />
817
+ <edge from-layer="38" from-port="8" to-layer="43" to-port="5" />
818
+ <edge from-layer="38" from-port="7" to-layer="43" to-port="4" />
819
+ <edge from-layer="39" from-port="0" to-layer="43" to-port="6" />
820
+ <edge from-layer="40" from-port="0" to-layer="43" to-port="7" />
821
+ <edge from-layer="41" from-port="0" to-layer="43" to-port="8" />
822
+ <edge from-layer="42" from-port="0" to-layer="43" to-port="9" />
823
+ <edge from-layer="43" from-port="10" to-layer="48" to-port="0" />
824
+ <edge from-layer="43" from-port="12" to-layer="48" to-port="2" />
825
+ <edge from-layer="43" from-port="11" to-layer="48" to-port="1" />
826
+ <edge from-layer="43" from-port="10" to-layer="44" to-port="1" />
827
+ <edge from-layer="43" from-port="11" to-layer="44" to-port="0" />
828
+ <edge from-layer="44" from-port="2" to-layer="46" to-port="0" />
829
+ <edge from-layer="45" from-port="0" to-layer="46" to-port="1" />
830
+ <edge from-layer="46" from-port="2" to-layer="48" to-port="3" />
831
+ <edge from-layer="47" from-port="0" to-layer="48" to-port="4" />
832
+ <edge from-layer="48" from-port="6" to-layer="49" to-port="0" />
833
+ <edge from-layer="48" from-port="5" to-layer="52" to-port="0" />
834
+ <edge from-layer="49" from-port="1" to-layer="50" to-port="0" />
835
+ <edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
836
+ <edge from-layer="52" from-port="1" to-layer="53" to-port="0" />
837
+ </edges>
838
+ <rt_info>
839
+ <add_attention_mask value="True" />
840
+ <add_prefix_space />
841
+ <add_special_tokens value="True" />
842
+ <bos_token_id value="0" />
843
+ <clean_up_tokenization_spaces />
844
+ <detokenizer_input_type value="i64" />
845
+ <eos_token_id value="2" />
846
+ <handle_special_tokens_with_re />
847
+ <max_length />
848
+ <number_of_inputs value="1" />
849
+ <openvino_tokenizers_version value="2025.2.0.1-567-7885335c24b" />
850
+ <openvino_version value="2025.2.0-19140-c01cd93e24d-releases/2025/2" />
851
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;type_id&quot;: 0}}], &quot;special_tokens&quot;: {&quot;&lt;/s>&quot;: {&quot;id&quot;: &quot;&lt;/s>&quot;, &quot;ids&quot;: [2], &quot;tokens&quot;: [&quot;&lt;/s>&quot;]}, &quot;&lt;s>&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;ids&quot;: [0], &quot;tokens&quot;: [&quot;&lt;s>&quot;]}}}" />
852
+ <original_tokenizer_class value="&lt;class 'transformers.models.xlm_roberta.tokenization_xlm_roberta_fast.XLMRobertaTokenizerFast'>" />
853
+ <pad_token_id value="1" />
854
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [0, -1, 2], &quot;type_ids&quot;: [0, 0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [0, -1, 2, 2, -2, 2], &quot;type_ids&quot;: [0, 0, 0, 0, 0, 0]}}" />
855
+ <sentencepiece_version value="0.2.1" />
856
+ <skip_special_tokens value="True" />
857
+ <streaming_detokenizer value="False" />
858
+ <tiktoken_version value="0.11.0" />
859
+ <tokenizer_output_type value="i64" />
860
+ <tokenizers_version value="0.21.4" />
861
+ <transformers_version value="4.53.3" />
862
+ <use_max_padding value="False" />
863
+ <use_sentencepiece_backend value="False" />
864
+ <utf8_replace_mode value="replace" />
865
+ <with_detokenizer value="True" />
866
+ </rt_info>
867
+ </net>
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }