OpenVINO
phi3
openvino-ci commited on
Commit
8f4daae
·
verified ·
1 Parent(s): 2f62415

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -13,7 +13,8 @@ This is a draft model that was trained with FastDraft to accompany [Phi-3-mini-4
13
  This is Phi-3-mini-FastDraft-50M model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to int8 by [NNCF](https://github.com/openvinotoolkit/nncf).
14
 
15
  > [!NOTE]
16
- > The model is optimized for inference on NPU.
 
17
 
18
  ## Quantization Parameters
19
 
@@ -81,7 +82,7 @@ More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://
81
 
82
  ## Legal Information
83
 
84
- The model is distributed under the [Intel Research Use License Agreement](https://huggingface.co/OpenVINO/Phi-3-mini-FastDraft-50M-int8-sym-ov/blob/main/LICENSE.md).
85
 
86
  ## Disclaimer
87
 
 
13
  This is Phi-3-mini-FastDraft-50M model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to int8 by [NNCF](https://github.com/openvinotoolkit/nncf).
14
 
15
  > [!NOTE]
16
+ > The model is optimized for inference on NPU using these [instructions.](https://docs.openvino.ai/2025/openvino-workflow-generative/inference-with-genai/inference-with-genai-on-npu.html#export-an-llm-model-via-hugging-face-optimum-intel)
17
+
18
 
19
  ## Quantization Parameters
20
 
 
82
 
83
  ## Legal Information
84
 
85
+ The model is distributed under the [Intel Research Use License Agreement](https://huggingface.co/OpenVINO/Llama-3.1-8B-Instruct-FastDraft-150M-int8-ov/blob/main/LICENSE.md).
86
 
87
  ## Disclaimer
88
 
chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
2
+ ' + message['content'] + '<|end|>
3
+ '}}{% elif message['role'] == 'user' %}{{'<|user|>
4
+ ' + message['content'] + '<|end|>
5
+ '}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
6
+ ' + message['content'] + '<|end|>
7
+ '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
8
+ ' }}{% else %}{{ eos_token }}{% endif %}
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_attn_implementation_autoset": true,
3
  "architectures": [
4
  "Phi3ForCausalLM"
5
  ],
@@ -27,7 +26,7 @@
27
  "sliding_window": 2047,
28
  "tie_word_embeddings": false,
29
  "torch_dtype": "float32",
30
- "transformers_version": "4.50.0",
31
  "use_cache": false,
32
  "vocab_size": 32064
33
  }
 
1
  {
 
2
  "architectures": [
3
  "Phi3ForCausalLM"
4
  ],
 
26
  "sliding_window": 2047,
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
29
+ "transformers_version": "4.53.3",
30
  "use_cache": false,
31
  "vocab_size": 32064
32
  }
generation_config.json CHANGED
@@ -1,8 +1,8 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 32000,
5
- "pad_token_id": 32000,
6
- "transformers_version": "4.50.0",
7
- "use_cache": false
8
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.53.3",
7
+ "use_cache": false
8
+ }
openvino_detokenizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03033c0408d4ab0211cc6ebed4996eba143e9eb7ff87cce30d46beb111c411d7
3
- size 467235
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b16873376036dd344f0ca3b4be43fd13243a0ab708eafa7560a301531093586f
3
+ size 467213
openvino_detokenizer.xml CHANGED
@@ -1,352 +1,351 @@
1
- <?xml version="1.0"?>
2
- <net name="detokenizer" version="11">
3
- <layers>
4
- <layer id="0" name="Parameter_29543" type="Parameter" version="opset1">
5
- <data shape="?,?" element_type="i64" />
6
- <output>
7
- <port id="0" precision="I64" names="Parameter_29543">
8
- <dim>-1</dim>
9
- <dim>-1</dim>
10
- </port>
11
- </output>
12
- </layer>
13
- <layer id="1" name="Convert_29718" 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_29495" type="Const" version="opset1">
29
- <data element_type="i32" shape="32011" offset="0" size="128044" />
30
- <output>
31
- <port id="0" precision="I32">
32
- <dim>32011</dim>
33
- </port>
34
- </output>
35
- </layer>
36
- <layer id="3" name="Constant_29497" type="Const" version="opset1">
37
- <data element_type="i32" shape="32011" offset="128044" size="128044" />
38
- <output>
39
- <port id="0" precision="I32">
40
- <dim>32011</dim>
41
- </port>
42
- </output>
43
- </layer>
44
- <layer id="4" name="Constant_29499" type="Const" version="opset1">
45
- <data element_type="u8" shape="211088" offset="256088" size="211088" />
46
- <output>
47
- <port id="0" precision="U8">
48
- <dim>211088</dim>
49
- </port>
50
- </output>
51
- </layer>
52
- <layer id="5" name="Slice_29548" type="Const" version="opset1">
53
- <data element_type="i32" shape="13" offset="467176" size="52" />
54
- <output>
55
- <port id="0" precision="I32">
56
- <dim>13</dim>
57
- </port>
58
- </output>
59
- </layer>
60
- <layer id="6" name="VocabDecoder_29550" 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>32011</dim>
69
- </port>
70
- <port id="2" precision="I32">
71
- <dim>32011</dim>
72
- </port>
73
- <port id="3" precision="U8">
74
- <dim>211088</dim>
75
- </port>
76
- <port id="4" precision="I32">
77
- <dim>13</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="Constant_29552" type="Const" version="opset1">
99
- <data element_type="u8" shape="3" offset="467228" size="3" />
100
- <output>
101
- <port id="0" precision="U8">
102
- <dim>3</dim>
103
- </port>
104
- </output>
105
- </layer>
106
- <layer id="8" name="Constant_29554" type="Const" version="opset1">
107
- <data element_type="u8" shape="1" offset="467231" size="1" />
108
- <output>
109
- <port id="0" precision="U8">
110
- <dim>1</dim>
111
- </port>
112
- </output>
113
- </layer>
114
- <layer id="9" name="RegexNormalization_29555" type="RegexNormalization" version="extension">
115
- <data global_replace="true" />
116
- <input>
117
- <port id="0" precision="I32">
118
- <dim>-1</dim>
119
- </port>
120
- <port id="1" precision="I32">
121
- <dim>-1</dim>
122
- </port>
123
- <port id="2" precision="U8">
124
- <dim>-1</dim>
125
- </port>
126
- <port id="3" precision="U8">
127
- <dim>3</dim>
128
- </port>
129
- <port id="4" precision="U8">
130
- <dim>1</dim>
131
- </port>
132
- </input>
133
- <output>
134
- <port id="5" precision="I32">
135
- <dim>-1</dim>
136
- </port>
137
- <port id="6" precision="I32">
138
- <dim>-1</dim>
139
- </port>
140
- <port id="7" precision="U8">
141
- <dim>-1</dim>
142
- </port>
143
- </output>
144
- </layer>
145
- <layer id="10" name="ByteFallback_29556" type="ByteFallback" version="extension">
146
- <input>
147
- <port id="0" precision="I32">
148
- <dim>-1</dim>
149
- </port>
150
- <port id="1" precision="I32">
151
- <dim>-1</dim>
152
- </port>
153
- <port id="2" precision="U8">
154
- <dim>-1</dim>
155
- </port>
156
- </input>
157
- <output>
158
- <port id="3" precision="I32">
159
- <dim>-1</dim>
160
- </port>
161
- <port id="4" precision="I32">
162
- <dim>-1</dim>
163
- </port>
164
- <port id="5" precision="U8">
165
- <dim>-1</dim>
166
- </port>
167
- </output>
168
- </layer>
169
- <layer id="11" name="FuzeRagged_29557" type="FuzeRagged" version="extension">
170
- <input>
171
- <port id="0" precision="I32">
172
- <dim>-1</dim>
173
- </port>
174
- <port id="1" precision="I32">
175
- <dim>-1</dim>
176
- </port>
177
- <port id="2" precision="I32">
178
- <dim>-1</dim>
179
- </port>
180
- <port id="3" precision="I32">
181
- <dim>-1</dim>
182
- </port>
183
- </input>
184
- <output>
185
- <port id="4" precision="I32">
186
- <dim>-1</dim>
187
- </port>
188
- <port id="5" precision="I32">
189
- <dim>-1</dim>
190
- </port>
191
- </output>
192
- </layer>
193
- <layer id="12" name="Constant_29559" type="Const" version="opset1">
194
- <data element_type="u8" shape="2" offset="467232" size="2" />
195
- <output>
196
- <port id="0" precision="U8">
197
- <dim>2</dim>
198
- </port>
199
- </output>
200
- </layer>
201
- <layer id="13" name="Constant_29561" type="Const" version="opset1">
202
- <data element_type="u8" shape="0" offset="467234" size="1" />
203
- <output>
204
- <port id="0" precision="U8">
205
- <dim>0</dim>
206
- </port>
207
- </output>
208
- </layer>
209
- <layer id="14" name="RegexNormalization_29562" type="RegexNormalization" version="extension">
210
- <data global_replace="true" />
211
- <input>
212
- <port id="0" precision="I32">
213
- <dim>-1</dim>
214
- </port>
215
- <port id="1" precision="I32">
216
- <dim>-1</dim>
217
- </port>
218
- <port id="2" precision="U8">
219
- <dim>-1</dim>
220
- </port>
221
- <port id="3" precision="U8">
222
- <dim>2</dim>
223
- </port>
224
- <port id="4" precision="U8">
225
- <dim>0</dim>
226
- </port>
227
- </input>
228
- <output>
229
- <port id="5" precision="I32">
230
- <dim>-1</dim>
231
- </port>
232
- <port id="6" precision="I32">
233
- <dim>-1</dim>
234
- </port>
235
- <port id="7" precision="U8">
236
- <dim>-1</dim>
237
- </port>
238
- </output>
239
- </layer>
240
- <layer id="15" name="UTF8Validate_29563" type="UTF8Validate" version="extension">
241
- <data replace_mode="true" />
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="I32">
255
- <dim>-1</dim>
256
- </port>
257
- <port id="4" precision="I32">
258
- <dim>-1</dim>
259
- </port>
260
- <port id="5" precision="U8">
261
- <dim>-1</dim>
262
- </port>
263
- </output>
264
- </layer>
265
- <layer id="16" name="StringTensorPack_29564" type="StringTensorPack" version="opset15">
266
- <input>
267
- <port id="0" precision="I32">
268
- <dim>-1</dim>
269
- </port>
270
- <port id="1" precision="I32">
271
- <dim>-1</dim>
272
- </port>
273
- <port id="2" precision="U8">
274
- <dim>-1</dim>
275
- </port>
276
- </input>
277
- <output>
278
- <port id="3" precision="STRING" names="Result_29565,string_output">
279
- <dim>-1</dim>
280
- </port>
281
- </output>
282
- </layer>
283
- <layer id="17" name="Result_29565" type="Result" version="opset1" output_names="Result_29565,string_output">
284
- <input>
285
- <port id="0" precision="STRING">
286
- <dim>-1</dim>
287
- </port>
288
- </input>
289
- </layer>
290
- </layers>
291
- <edges>
292
- <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
293
- <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
294
- <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
295
- <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
296
- <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
297
- <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
298
- <edge from-layer="6" from-port="7" to-layer="9" to-port="0" />
299
- <edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
300
- <edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
301
- <edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
302
- <edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
303
- <edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
304
- <edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
305
- <edge from-layer="9" from-port="5" to-layer="10" to-port="0" />
306
- <edge from-layer="9" from-port="6" to-layer="10" to-port="1" />
307
- <edge from-layer="9" from-port="7" to-layer="10" to-port="2" />
308
- <edge from-layer="10" from-port="3" to-layer="11" to-port="2" />
309
- <edge from-layer="10" from-port="4" to-layer="11" to-port="3" />
310
- <edge from-layer="10" from-port="5" to-layer="14" to-port="2" />
311
- <edge from-layer="11" from-port="4" to-layer="14" to-port="0" />
312
- <edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
313
- <edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
314
- <edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
315
- <edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
316
- <edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
317
- <edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
318
- <edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
319
- <edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
320
- <edge from-layer="15" from-port="5" to-layer="16" to-port="2" />
321
- <edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
322
- </edges>
323
- <rt_info>
324
- <add_attention_mask value="True" />
325
- <add_prefix_space />
326
- <add_special_tokens value="True" />
327
- <bos_token_id value="1" />
328
- <chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
329
- <clean_up_tokenization_spaces />
330
- <detokenizer_input_type value="i64" />
331
- <eos_token_id value="32000" />
332
- <handle_special_tokens_with_re />
333
- <max_length />
334
- <number_of_inputs value="1" />
335
- <openvino_tokenizers_version value="2025.2.0.0-529-cc2fccf72a1" />
336
- <openvino_version value="2025.2.0-18537-69f578c0b73" />
337
- <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;|endoftext|>&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;|endoftext|>&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 1}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {&quot;&lt;s>&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;ids&quot;: [1], &quot;tokens&quot;: [&quot;&lt;s>&quot;]}, &quot;&lt;|endoftext|>&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;ids&quot;: [32000], &quot;tokens&quot;: [&quot;&lt;|endoftext|>&quot;]}}}" />
338
- <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
339
- <pad_token_id value="32000" />
340
- <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [1, -1, 32000], &quot;type_ids&quot;: [0, 0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [1, -1, 32000, 1, -2, 32000], &quot;type_ids&quot;: [0, 0, 0, 1, 1, 1]}}" />
341
- <sentencepiece_version value="0.2.0" />
342
- <skip_special_tokens value="True" />
343
- <streaming_detokenizer value="False" />
344
- <tokenizer_output_type value="i64" />
345
- <tokenizers_version value="0.21.1" />
346
- <transformers_version value="4.50.0" />
347
- <use_max_padding value="False" />
348
- <use_sentencepiece_backend value="False" />
349
- <utf8_replace_mode value="replace" />
350
- <with_detokenizer value="True" />
351
- </rt_info>
352
- </net>
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_35410" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_35410">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_35614" 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_35366" type="Const" version="opset1">
29
+ <data element_type="i32" shape="32011" offset="0" size="128044" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>32011</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_35368" type="Const" version="opset1">
37
+ <data element_type="i32" shape="32011" offset="128044" size="128044" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>32011</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_35370" type="Const" version="opset1">
45
+ <data element_type="u8" shape="211066" offset="256088" size="211066" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>211066</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_35415" type="Const" version="opset1">
53
+ <data element_type="i32" shape="13" offset="467154" size="52" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>13</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_35417" 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>32011</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>32011</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>211066</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>13</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="Constant_35419" type="Const" version="opset1">
99
+ <data element_type="u8" shape="3" offset="467206" size="3" />
100
+ <output>
101
+ <port id="0" precision="U8">
102
+ <dim>3</dim>
103
+ </port>
104
+ </output>
105
+ </layer>
106
+ <layer id="8" name="Constant_35421" type="Const" version="opset1">
107
+ <data element_type="u8" shape="1" offset="467209" size="1" />
108
+ <output>
109
+ <port id="0" precision="U8">
110
+ <dim>1</dim>
111
+ </port>
112
+ </output>
113
+ </layer>
114
+ <layer id="9" name="RegexNormalization_35422" type="RegexNormalization" version="extension">
115
+ <data global_replace="true" />
116
+ <input>
117
+ <port id="0" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ <port id="1" precision="I32">
121
+ <dim>-1</dim>
122
+ </port>
123
+ <port id="2" precision="U8">
124
+ <dim>-1</dim>
125
+ </port>
126
+ <port id="3" precision="U8">
127
+ <dim>3</dim>
128
+ </port>
129
+ <port id="4" precision="U8">
130
+ <dim>1</dim>
131
+ </port>
132
+ </input>
133
+ <output>
134
+ <port id="5" precision="I32">
135
+ <dim>-1</dim>
136
+ </port>
137
+ <port id="6" precision="I32">
138
+ <dim>-1</dim>
139
+ </port>
140
+ <port id="7" precision="U8">
141
+ <dim>-1</dim>
142
+ </port>
143
+ </output>
144
+ </layer>
145
+ <layer id="10" name="ByteFallback_35423" type="ByteFallback" version="extension">
146
+ <input>
147
+ <port id="0" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="1" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="2" precision="U8">
154
+ <dim>-1</dim>
155
+ </port>
156
+ </input>
157
+ <output>
158
+ <port id="3" precision="I32">
159
+ <dim>-1</dim>
160
+ </port>
161
+ <port id="4" precision="I32">
162
+ <dim>-1</dim>
163
+ </port>
164
+ <port id="5" precision="U8">
165
+ <dim>-1</dim>
166
+ </port>
167
+ </output>
168
+ </layer>
169
+ <layer id="11" name="FuzeRagged_35424" type="FuzeRagged" version="extension">
170
+ <input>
171
+ <port id="0" precision="I32">
172
+ <dim>-1</dim>
173
+ </port>
174
+ <port id="1" precision="I32">
175
+ <dim>-1</dim>
176
+ </port>
177
+ <port id="2" precision="I32">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="3" precision="I32">
181
+ <dim>-1</dim>
182
+ </port>
183
+ </input>
184
+ <output>
185
+ <port id="4" precision="I32">
186
+ <dim>-1</dim>
187
+ </port>
188
+ <port id="5" precision="I32">
189
+ <dim>-1</dim>
190
+ </port>
191
+ </output>
192
+ </layer>
193
+ <layer id="12" name="Constant_35426" type="Const" version="opset1">
194
+ <data element_type="u8" shape="2" offset="467210" size="2" />
195
+ <output>
196
+ <port id="0" precision="U8">
197
+ <dim>2</dim>
198
+ </port>
199
+ </output>
200
+ </layer>
201
+ <layer id="13" name="Constant_35428" type="Const" version="opset1">
202
+ <data element_type="u8" shape="0" offset="467212" size="1" />
203
+ <output>
204
+ <port id="0" precision="U8">
205
+ <dim>0</dim>
206
+ </port>
207
+ </output>
208
+ </layer>
209
+ <layer id="14" name="RegexNormalization_35429" type="RegexNormalization" version="extension">
210
+ <data global_replace="true" />
211
+ <input>
212
+ <port id="0" precision="I32">
213
+ <dim>-1</dim>
214
+ </port>
215
+ <port id="1" precision="I32">
216
+ <dim>-1</dim>
217
+ </port>
218
+ <port id="2" precision="U8">
219
+ <dim>-1</dim>
220
+ </port>
221
+ <port id="3" precision="U8">
222
+ <dim>2</dim>
223
+ </port>
224
+ <port id="4" precision="U8">
225
+ <dim>0</dim>
226
+ </port>
227
+ </input>
228
+ <output>
229
+ <port id="5" precision="I32">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="6" precision="I32">
233
+ <dim>-1</dim>
234
+ </port>
235
+ <port id="7" precision="U8">
236
+ <dim>-1</dim>
237
+ </port>
238
+ </output>
239
+ </layer>
240
+ <layer id="15" name="UTF8Validate_35430" type="UTF8Validate" version="extension">
241
+ <data replace_mode="true" />
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="I32">
255
+ <dim>-1</dim>
256
+ </port>
257
+ <port id="4" precision="I32">
258
+ <dim>-1</dim>
259
+ </port>
260
+ <port id="5" precision="U8">
261
+ <dim>-1</dim>
262
+ </port>
263
+ </output>
264
+ </layer>
265
+ <layer id="16" name="StringTensorPack_35431" type="StringTensorPack" version="opset15">
266
+ <input>
267
+ <port id="0" precision="I32">
268
+ <dim>-1</dim>
269
+ </port>
270
+ <port id="1" precision="I32">
271
+ <dim>-1</dim>
272
+ </port>
273
+ <port id="2" precision="U8">
274
+ <dim>-1</dim>
275
+ </port>
276
+ </input>
277
+ <output>
278
+ <port id="3" precision="STRING" names="Result_35432,string_output">
279
+ <dim>-1</dim>
280
+ </port>
281
+ </output>
282
+ </layer>
283
+ <layer id="17" name="Result_35432" type="Result" version="opset1" output_names="Result_35432,string_output">
284
+ <input>
285
+ <port id="0" precision="STRING">
286
+ <dim>-1</dim>
287
+ </port>
288
+ </input>
289
+ </layer>
290
+ </layers>
291
+ <edges>
292
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
293
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
294
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
295
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
296
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
297
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
298
+ <edge from-layer="6" from-port="6" to-layer="11" to-port="1" />
299
+ <edge from-layer="6" from-port="5" to-layer="11" to-port="0" />
300
+ <edge from-layer="6" from-port="8" to-layer="9" to-port="1" />
301
+ <edge from-layer="6" from-port="7" to-layer="9" to-port="0" />
302
+ <edge from-layer="6" from-port="9" to-layer="9" to-port="2" />
303
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
304
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
305
+ <edge from-layer="9" from-port="5" to-layer="10" to-port="0" />
306
+ <edge from-layer="9" from-port="6" to-layer="10" to-port="1" />
307
+ <edge from-layer="9" from-port="7" to-layer="10" to-port="2" />
308
+ <edge from-layer="10" from-port="3" to-layer="11" to-port="2" />
309
+ <edge from-layer="10" from-port="4" to-layer="11" to-port="3" />
310
+ <edge from-layer="10" from-port="5" to-layer="14" to-port="2" />
311
+ <edge from-layer="11" from-port="5" to-layer="14" to-port="1" />
312
+ <edge from-layer="11" from-port="4" to-layer="14" to-port="0" />
313
+ <edge from-layer="12" from-port="0" to-layer="14" to-port="3" />
314
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="4" />
315
+ <edge from-layer="14" from-port="5" to-layer="15" to-port="0" />
316
+ <edge from-layer="14" from-port="6" to-layer="15" to-port="1" />
317
+ <edge from-layer="14" from-port="7" to-layer="15" to-port="2" />
318
+ <edge from-layer="15" from-port="3" to-layer="16" to-port="0" />
319
+ <edge from-layer="15" from-port="4" to-layer="16" to-port="1" />
320
+ <edge from-layer="15" from-port="5" to-layer="16" to-port="2" />
321
+ <edge from-layer="16" from-port="3" to-layer="17" to-port="0" />
322
+ </edges>
323
+ <rt_info>
324
+ <add_attention_mask value="True" />
325
+ <add_prefix_space />
326
+ <add_special_tokens value="True" />
327
+ <bos_token_id value="1" />
328
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
329
+ <clean_up_tokenization_spaces />
330
+ <detokenizer_input_type value="i64" />
331
+ <eos_token_id value="32000" />
332
+ <handle_special_tokens_with_re />
333
+ <max_length />
334
+ <number_of_inputs value="1" />
335
+ <openvino_tokenizers_version value="2025.4.0.0-615-c8aad078405" />
336
+ <openvino_version value="2025.4.0-20104-e6264070ff2" />
337
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
338
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
339
+ <pad_token_id value="32000" />
340
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
341
+ <skip_special_tokens value="True" />
342
+ <streaming_detokenizer value="False" />
343
+ <tokenizer_output_type value="i64" />
344
+ <tokenizers_version value="0.21.4" />
345
+ <transformers_version value="4.53.3" />
346
+ <use_max_padding value="False" />
347
+ <use_sentencepiece_backend value="False" />
348
+ <utf8_replace_mode value="replace" />
349
+ <with_detokenizer value="True" />
350
+ </rt_info>
351
+ </net>
 
openvino_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b7a1987637456f8d3ecbc666f5ae9711ede2b727008d7da5fbcf425f13ed991
3
- size 52320840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a55e42fc51ad39da4542d98e4e38084cd6fac494e7af98a2edc5cf5b1598bc
3
+ size 52320845
openvino_model.xml CHANGED
The diff for this file is too large to render. See raw diff
 
openvino_tokenizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1edbeaaa6cecbc1a010999b64abf8d51662d627dd7cf7f628c47bb95da091126
3
- size 1881991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c2518be900e9686e4e82e4d7b44ed8790185d7e14166e35ad9d42b843423f35
3
+ size 1869678
openvino_tokenizer.xml CHANGED
@@ -1,848 +1,793 @@
1
- <?xml version="1.0"?>
2
- <net name="tokenizer" version="11">
3
- <layers>
4
- <layer id="0" name="Parameter_29407" type="Parameter" version="opset1">
5
- <data shape="?" element_type="string" />
6
- <output>
7
- <port id="0" precision="STRING" names="Parameter_29407">
8
- <dim>-1</dim>
9
- </port>
10
- </output>
11
- </layer>
12
- <layer id="1" name="Constant_29524" 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_29525" 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_29526" type="Const" version="opset1">
25
- <data element_type="i32" shape="1" offset="4" 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_29413" 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_29408" 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_29409" 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_29410" 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_29411" 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_29412" 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_29414" 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_29415" 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_29416" 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_29417" 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_29418" 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_29419" 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_29420" 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_29482" type="Const" version="opset1">
155
- <data element_type="u8" shape="328" offset="24" size="328" />
156
- <output>
157
- <port id="0" precision="U8">
158
- <dim>328</dim>
159
- </port>
160
- </output>
161
- </layer>
162
- <layer id="18" name="SpecialTokensSplit_29483" 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>328</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_29485" type="Const" version="opset1">
205
- <data element_type="u8" shape="13" offset="352" size="13" />
206
- <output>
207
- <port id="0" precision="U8">
208
- <dim>13</dim>
209
- </port>
210
- </output>
211
- </layer>
212
- <layer id="20" name="Constant_29487" type="Const" version="opset1">
213
- <data element_type="u8" shape="5" offset="365" size="5" />
214
- <output>
215
- <port id="0" precision="U8">
216
- <dim>5</dim>
217
- </port>
218
- </output>
219
- </layer>
220
- <layer id="21" name="RegexNormalization_29488" type="RegexNormalization" version="extension">
221
- <data global_replace="true" />
222
- <input>
223
- <port id="0" precision="I32">
224
- <dim>-1</dim>
225
- </port>
226
- <port id="1" precision="I32">
227
- <dim>-1</dim>
228
- </port>
229
- <port id="2" precision="U8">
230
- <dim>-1</dim>
231
- </port>
232
- <port id="3" precision="BOOL">
233
- <dim>-1</dim>
234
- </port>
235
- <port id="4" precision="U8">
236
- <dim>13</dim>
237
- </port>
238
- <port id="5" precision="U8">
239
- <dim>5</dim>
240
- </port>
241
- </input>
242
- <output>
243
- <port id="6" precision="I32">
244
- <dim>-1</dim>
245
- </port>
246
- <port id="7" precision="I32">
247
- <dim>-1</dim>
248
- </port>
249
- <port id="8" precision="U8">
250
- <dim>-1</dim>
251
- </port>
252
- <port id="9" precision="BOOL">
253
- <dim>-1</dim>
254
- </port>
255
- </output>
256
- </layer>
257
- <layer id="22" name="Constant_29490" type="Const" version="opset1">
258
- <data element_type="u8" shape="1" offset="370" size="1" />
259
- <output>
260
- <port id="0" precision="U8">
261
- <dim>1</dim>
262
- </port>
263
- </output>
264
- </layer>
265
- <layer id="23" name="Constant_29492" type="Const" version="opset1">
266
- <data element_type="u8" shape="3" offset="371" size="3" />
267
- <output>
268
- <port id="0" precision="U8">
269
- <dim>3</dim>
270
- </port>
271
- </output>
272
- </layer>
273
- <layer id="24" name="RegexNormalization_29493" type="RegexNormalization" version="extension">
274
- <data global_replace="true" />
275
- <input>
276
- <port id="0" precision="I32">
277
- <dim>-1</dim>
278
- </port>
279
- <port id="1" precision="I32">
280
- <dim>-1</dim>
281
- </port>
282
- <port id="2" precision="U8">
283
- <dim>-1</dim>
284
- </port>
285
- <port id="3" precision="BOOL">
286
- <dim>-1</dim>
287
- </port>
288
- <port id="4" precision="U8">
289
- <dim>1</dim>
290
- </port>
291
- <port id="5" precision="U8">
292
- <dim>3</dim>
293
- </port>
294
- </input>
295
- <output>
296
- <port id="6" precision="I32">
297
- <dim>-1</dim>
298
- </port>
299
- <port id="7" precision="I32">
300
- <dim>-1</dim>
301
- </port>
302
- <port id="8" precision="U8">
303
- <dim>-1</dim>
304
- </port>
305
- <port id="9" precision="BOOL">
306
- <dim>-1</dim>
307
- </port>
308
- </output>
309
- </layer>
310
- <layer id="25" name="Constant_29495" type="Const" version="opset1">
311
- <data element_type="i32" shape="32011" offset="374" size="128044" />
312
- <output>
313
- <port id="0" precision="I32">
314
- <dim>32011</dim>
315
- </port>
316
- </output>
317
- </layer>
318
- <layer id="26" name="Constant_29497" type="Const" version="opset1">
319
- <data element_type="i32" shape="32011" offset="128418" size="128044" />
320
- <output>
321
- <port id="0" precision="I32">
322
- <dim>32011</dim>
323
- </port>
324
- </output>
325
- </layer>
326
- <layer id="27" name="Constant_29499" type="Const" version="opset1">
327
- <data element_type="u8" shape="211088" offset="256462" size="211088" />
328
- <output>
329
- <port id="0" precision="U8">
330
- <dim>211088</dim>
331
- </port>
332
- </output>
333
- </layer>
334
- <layer id="28" name="Constant_29507" type="Const" version="opset1">
335
- <data element_type="i32" shape="61249" offset="467550" size="244996" />
336
- <output>
337
- <port id="0" precision="I32">
338
- <dim>61249</dim>
339
- </port>
340
- </output>
341
- </layer>
342
- <layer id="29" name="Constant_29509" type="Const" version="opset1">
343
- <data element_type="i32" shape="61249" offset="712546" size="244996" />
344
- <output>
345
- <port id="0" precision="I32">
346
- <dim>61249</dim>
347
- </port>
348
- </output>
349
- </layer>
350
- <layer id="30" name="Constant_29511" type="Const" version="opset1">
351
- <data element_type="u8" shape="254123" offset="957542" size="254123" />
352
- <output>
353
- <port id="0" precision="U8">
354
- <dim>254123</dim>
355
- </port>
356
- </output>
357
- </layer>
358
- <layer id="31" name="Constant_29513" type="Const" version="opset1">
359
- <data element_type="i32" shape="61249" offset="1211665" size="244996" />
360
- <output>
361
- <port id="0" precision="I32">
362
- <dim>61249</dim>
363
- </port>
364
- </output>
365
- </layer>
366
- <layer id="32" name="Constant_29515" type="Const" version="opset1">
367
- <data element_type="i32" shape="61249" offset="1456661" size="244996" />
368
- <output>
369
- <port id="0" precision="I32">
370
- <dim>61249</dim>
371
- </port>
372
- </output>
373
- </layer>
374
- <layer id="33" name="Constant_29517" type="Const" version="opset1">
375
- <data element_type="u8" shape="167806" offset="1701657" size="167806" />
376
- <output>
377
- <port id="0" precision="U8">
378
- <dim>167806</dim>
379
- </port>
380
- </output>
381
- </layer>
382
- <layer id="34" name="Constant_29501" type="Const" version="opset1">
383
- <data element_type="i32" shape="475" offset="1869463" size="1900" />
384
- <output>
385
- <port id="0" precision="I32">
386
- <dim>475</dim>
387
- </port>
388
- </output>
389
- </layer>
390
- <layer id="35" name="Constant_29503" type="Const" version="opset1">
391
- <data element_type="i32" shape="475" offset="1871363" size="1900" />
392
- <output>
393
- <port id="0" precision="I32">
394
- <dim>475</dim>
395
- </port>
396
- </output>
397
- </layer>
398
- <layer id="36" name="Constant_29505" type="Const" version="opset1">
399
- <data element_type="u8" shape="6808" offset="1873263" size="6808" />
400
- <output>
401
- <port id="0" precision="U8">
402
- <dim>6808</dim>
403
- </port>
404
- </output>
405
- </layer>
406
- <layer id="37" name="Constant_29518" type="Const" version="opset1">
407
- <data element_type="i32" shape="475" offset="1880071" size="1900" />
408
- <output>
409
- <port id="0" precision="I32">
410
- <dim>475</dim>
411
- </port>
412
- </output>
413
- </layer>
414
- <layer id="38" name="BPETokenizer_29519" type="BPETokenizer" version="extension">
415
- <data unk_token="&lt;unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="20000" />
416
- <input>
417
- <port id="0" precision="I32">
418
- <dim>-1</dim>
419
- </port>
420
- <port id="1" precision="I32">
421
- <dim>-1</dim>
422
- </port>
423
- <port id="2" precision="I32">
424
- <dim>-1</dim>
425
- </port>
426
- <port id="3" precision="I32">
427
- <dim>-1</dim>
428
- </port>
429
- <port id="4" precision="U8">
430
- <dim>-1</dim>
431
- </port>
432
- <port id="5" precision="I32">
433
- <dim>32011</dim>
434
- </port>
435
- <port id="6" precision="I32">
436
- <dim>32011</dim>
437
- </port>
438
- <port id="7" precision="U8">
439
- <dim>211088</dim>
440
- </port>
441
- <port id="8" precision="I32">
442
- <dim>61249</dim>
443
- </port>
444
- <port id="9" precision="I32">
445
- <dim>61249</dim>
446
- </port>
447
- <port id="10" precision="U8">
448
- <dim>254123</dim>
449
- </port>
450
- <port id="11" precision="I32">
451
- <dim>61249</dim>
452
- </port>
453
- <port id="12" precision="I32">
454
- <dim>61249</dim>
455
- </port>
456
- <port id="13" precision="U8">
457
- <dim>167806</dim>
458
- </port>
459
- <port id="14" precision="I32">
460
- <dim>475</dim>
461
- </port>
462
- <port id="15" precision="I32">
463
- <dim>475</dim>
464
- </port>
465
- <port id="16" precision="U8">
466
- <dim>6808</dim>
467
- </port>
468
- <port id="17" precision="I32">
469
- <dim>475</dim>
470
- </port>
471
- </input>
472
- <output>
473
- <port id="18" precision="I32">
474
- <dim>-1</dim>
475
- </port>
476
- <port id="19" precision="I32">
477
- <dim>-1</dim>
478
- </port>
479
- <port id="20" precision="I32">
480
- <dim>-1</dim>
481
- </port>
482
- </output>
483
- </layer>
484
- <layer id="39" name="Subtract_29520" type="Subtract" version="opset1">
485
- <data auto_broadcast="numpy" />
486
- <input>
487
- <port id="0" precision="I32">
488
- <dim>-1</dim>
489
- </port>
490
- <port id="1" precision="I32">
491
- <dim>-1</dim>
492
- </port>
493
- </input>
494
- <output>
495
- <port id="2" precision="I32">
496
- <dim>-1</dim>
497
- </port>
498
- </output>
499
- </layer>
500
- <layer id="40" name="Constant_29521" type="Const" version="opset1">
501
- <data element_type="i32" shape="" offset="1881971" size="4" />
502
- <output>
503
- <port id="0" precision="I32" />
504
- </output>
505
- </layer>
506
- <layer id="41" name="Minimum_29522" type="Minimum" version="opset1">
507
- <data auto_broadcast="numpy" />
508
- <input>
509
- <port id="0" precision="I32">
510
- <dim>-1</dim>
511
- </port>
512
- <port id="1" precision="I32" />
513
- </input>
514
- <output>
515
- <port id="2" precision="I32">
516
- <dim>-1</dim>
517
- </port>
518
- </output>
519
- </layer>
520
- <layer id="42" name="Subtract_29523" type="Subtract" version="opset1">
521
- <data auto_broadcast="numpy" />
522
- <input>
523
- <port id="0" precision="I32">
524
- <dim>-1</dim>
525
- </port>
526
- <port id="1" precision="I32">
527
- <dim>-1</dim>
528
- </port>
529
- </input>
530
- <output>
531
- <port id="2" precision="I32">
532
- <dim>-1</dim>
533
- </port>
534
- </output>
535
- </layer>
536
- <layer id="43" name="Constant_29527" type="Const" version="opset1">
537
- <data element_type="i32" shape="" offset="0" size="4" />
538
- <output>
539
- <port id="0" precision="I32" />
540
- </output>
541
- </layer>
542
- <layer id="44" name="Constant_29528" type="Const" version="opset1">
543
- <data element_type="i32" shape="" offset="4" size="4" />
544
- <output>
545
- <port id="0" precision="I32" />
546
- </output>
547
- </layer>
548
- <layer id="45" name="Constant_29529" type="Const" version="opset1">
549
- <data element_type="i32" shape="1" offset="1881975" size="4" />
550
- <output>
551
- <port id="0" precision="I32">
552
- <dim>1</dim>
553
- </port>
554
- </output>
555
- </layer>
556
- <layer id="46" name="Constant_29530" type="Const" version="opset1">
557
- <data element_type="i32" shape="3" offset="1881979" size="12" />
558
- <output>
559
- <port id="0" precision="I32">
560
- <dim>3</dim>
561
- </port>
562
- </output>
563
- </layer>
564
- <layer id="47" name="CombineSegments_29531" type="CombineSegments" version="extension">
565
- <input>
566
- <port id="0" precision="I32" />
567
- <port id="1" precision="I32" />
568
- <port id="2" precision="I32">
569
- <dim>1</dim>
570
- </port>
571
- <port id="3" precision="I32">
572
- <dim>-1</dim>
573
- </port>
574
- <port id="4" precision="I32">
575
- <dim>-1</dim>
576
- </port>
577
- <port id="5" precision="I32">
578
- <dim>-1</dim>
579
- </port>
580
- <port id="6" precision="I32" />
581
- <port id="7" precision="I32" />
582
- <port id="8" precision="I32">
583
- <dim>1</dim>
584
- </port>
585
- <port id="9" precision="I32">
586
- <dim>3</dim>
587
- </port>
588
- </input>
589
- <output>
590
- <port id="10" precision="I32">
591
- <dim>-1</dim>
592
- </port>
593
- <port id="11" precision="I32">
594
- <dim>-1</dim>
595
- </port>
596
- <port id="12" precision="I32">
597
- <dim>-1</dim>
598
- </port>
599
- <port id="13" precision="I32">
600
- <dim>-1</dim>
601
- </port>
602
- <port id="14" precision="I32">
603
- <dim>-1</dim>
604
- </port>
605
- <port id="15" precision="I32">
606
- <dim>-1</dim>
607
- </port>
608
- </output>
609
- </layer>
610
- <layer id="48" name="Subtract_29532" type="Subtract" version="opset1">
611
- <data auto_broadcast="numpy" />
612
- <input>
613
- <port id="0" precision="I32">
614
- <dim>-1</dim>
615
- </port>
616
- <port id="1" precision="I32">
617
- <dim>-1</dim>
618
- </port>
619
- </input>
620
- <output>
621
- <port id="2" precision="I32">
622
- <dim>-1</dim>
623
- </port>
624
- </output>
625
- </layer>
626
- <layer id="49" name="Constant_29533" type="Const" version="opset1">
627
- <data element_type="i32" shape="" offset="0" size="4" />
628
- <output>
629
- <port id="0" precision="I32" />
630
- </output>
631
- </layer>
632
- <layer id="50" name="ReduceMax_29534" type="ReduceMax" version="opset1">
633
- <data keep_dims="false" />
634
- <input>
635
- <port id="0" precision="I32">
636
- <dim>-1</dim>
637
- </port>
638
- <port id="1" precision="I32" />
639
- </input>
640
- <output>
641
- <port id="2" precision="I32" />
642
- </output>
643
- </layer>
644
- <layer id="51" name="Constant_29535" type="Const" version="opset1">
645
- <data element_type="i32" shape="" offset="1881975" size="4" />
646
- <output>
647
- <port id="0" precision="I32" />
648
- </output>
649
- </layer>
650
- <layer id="52" name="RaggedToDense_29536" type="RaggedToDense" version="extension">
651
- <data pad_right="false" m_pad_max_length="false" />
652
- <input>
653
- <port id="0" precision="I32">
654
- <dim>-1</dim>
655
- </port>
656
- <port id="1" precision="I32">
657
- <dim>-1</dim>
658
- </port>
659
- <port id="2" precision="I32">
660
- <dim>-1</dim>
661
- </port>
662
- <port id="3" precision="I32" />
663
- <port id="4" precision="I32" />
664
- </input>
665
- <output>
666
- <port id="5" precision="I32">
667
- <dim>-1</dim>
668
- <dim>-1</dim>
669
- </port>
670
- <port id="6" precision="BOOL">
671
- <dim>-1</dim>
672
- <dim>-1</dim>
673
- </port>
674
- </output>
675
- </layer>
676
- <layer id="53" name="Convert_29537" type="Convert" version="opset1">
677
- <data destination_type="i32" />
678
- <input>
679
- <port id="0" precision="BOOL">
680
- <dim>-1</dim>
681
- <dim>-1</dim>
682
- </port>
683
- </input>
684
- <output>
685
- <port id="1" precision="I32">
686
- <dim>-1</dim>
687
- <dim>-1</dim>
688
- </port>
689
- </output>
690
- </layer>
691
- <layer id="54" name="Convert_29537.0" type="Convert" version="opset1">
692
- <data destination_type="i64" />
693
- <input>
694
- <port id="0" precision="I32">
695
- <dim>-1</dim>
696
- <dim>-1</dim>
697
- </port>
698
- </input>
699
- <output>
700
- <port id="1" precision="I64" names="attention_mask">
701
- <dim>-1</dim>
702
- <dim>-1</dim>
703
- </port>
704
- </output>
705
- </layer>
706
- <layer id="56" name="RaggedToDense_29536.0" 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="input_ids">
716
- <dim>-1</dim>
717
- <dim>-1</dim>
718
- </port>
719
- </output>
720
- </layer>
721
- <layer id="57" name="Result_29540" type="Result" version="opset1" output_names="input_ids">
722
- <input>
723
- <port id="0" precision="I64">
724
- <dim>-1</dim>
725
- <dim>-1</dim>
726
- </port>
727
- </input>
728
- </layer>
729
- <layer id="55" name="Result_29542" type="Result" version="opset1" output_names="attention_mask">
730
- <input>
731
- <port id="0" precision="I64">
732
- <dim>-1</dim>
733
- <dim>-1</dim>
734
- </port>
735
- </input>
736
- </layer>
737
- </layers>
738
- <edges>
739
- <edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
740
- <edge from-layer="1" from-port="0" to-layer="47" to-port="0" />
741
- <edge from-layer="2" from-port="0" to-layer="47" to-port="1" />
742
- <edge from-layer="3" from-port="0" to-layer="47" to-port="2" />
743
- <edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
744
- <edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
745
- <edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
746
- <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
747
- <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
748
- <edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
749
- <edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
750
- <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
751
- <edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
752
- <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
753
- <edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
754
- <edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
755
- <edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
756
- <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
757
- <edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
758
- <edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
759
- <edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
760
- <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
761
- <edge from-layer="18" from-port="11" to-layer="21" to-port="3" />
762
- <edge from-layer="18" from-port="8" to-layer="21" to-port="0" />
763
- <edge from-layer="18" from-port="7" to-layer="38" to-port="1" />
764
- <edge from-layer="18" from-port="6" to-layer="38" to-port="0" />
765
- <edge from-layer="18" from-port="9" to-layer="21" to-port="1" />
766
- <edge from-layer="18" from-port="10" to-layer="21" to-port="2" />
767
- <edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
768
- <edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
769
- <edge from-layer="21" from-port="9" to-layer="24" to-port="3" />
770
- <edge from-layer="21" from-port="6" to-layer="24" to-port="0" />
771
- <edge from-layer="21" from-port="7" to-layer="24" to-port="1" />
772
- <edge from-layer="21" from-port="8" to-layer="24" to-port="2" />
773
- <edge from-layer="22" from-port="0" to-layer="24" to-port="4" />
774
- <edge from-layer="23" from-port="0" to-layer="24" to-port="5" />
775
- <edge from-layer="24" from-port="6" to-layer="38" to-port="2" />
776
- <edge from-layer="24" from-port="7" to-layer="38" to-port="3" />
777
- <edge from-layer="24" from-port="8" to-layer="38" to-port="4" />
778
- <edge from-layer="25" from-port="0" to-layer="38" to-port="5" />
779
- <edge from-layer="26" from-port="0" to-layer="38" to-port="6" />
780
- <edge from-layer="27" from-port="0" to-layer="38" to-port="7" />
781
- <edge from-layer="28" from-port="0" to-layer="38" to-port="8" />
782
- <edge from-layer="29" from-port="0" to-layer="38" to-port="9" />
783
- <edge from-layer="30" from-port="0" to-layer="38" to-port="10" />
784
- <edge from-layer="31" from-port="0" to-layer="38" to-port="11" />
785
- <edge from-layer="32" from-port="0" to-layer="38" to-port="12" />
786
- <edge from-layer="33" from-port="0" to-layer="38" to-port="13" />
787
- <edge from-layer="34" from-port="0" to-layer="38" to-port="14" />
788
- <edge from-layer="35" from-port="0" to-layer="38" to-port="15" />
789
- <edge from-layer="36" from-port="0" to-layer="38" to-port="16" />
790
- <edge from-layer="37" from-port="0" to-layer="38" to-port="17" />
791
- <edge from-layer="38" from-port="19" to-layer="39" to-port="0" />
792
- <edge from-layer="38" from-port="18" to-layer="39" to-port="1" />
793
- <edge from-layer="38" from-port="19" to-layer="42" to-port="0" />
794
- <edge from-layer="38" from-port="19" to-layer="47" to-port="4" />
795
- <edge from-layer="38" from-port="20" to-layer="47" to-port="5" />
796
- <edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
797
- <edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
798
- <edge from-layer="41" from-port="2" to-layer="42" to-port="1" />
799
- <edge from-layer="42" from-port="2" to-layer="47" to-port="3" />
800
- <edge from-layer="43" from-port="0" to-layer="47" to-port="6" />
801
- <edge from-layer="44" from-port="0" to-layer="47" to-port="7" />
802
- <edge from-layer="45" from-port="0" to-layer="47" to-port="8" />
803
- <edge from-layer="46" from-port="0" to-layer="47" to-port="9" />
804
- <edge from-layer="47" from-port="11" to-layer="48" to-port="0" />
805
- <edge from-layer="47" from-port="10" to-layer="48" to-port="1" />
806
- <edge from-layer="47" from-port="10" to-layer="52" to-port="0" />
807
- <edge from-layer="47" from-port="11" to-layer="52" to-port="1" />
808
- <edge from-layer="47" from-port="12" to-layer="52" to-port="2" />
809
- <edge from-layer="48" from-port="2" to-layer="50" to-port="0" />
810
- <edge from-layer="49" from-port="0" to-layer="50" to-port="1" />
811
- <edge from-layer="50" from-port="2" to-layer="52" to-port="3" />
812
- <edge from-layer="51" from-port="0" to-layer="52" to-port="4" />
813
- <edge from-layer="52" from-port="6" to-layer="53" to-port="0" />
814
- <edge from-layer="52" from-port="5" to-layer="56" to-port="0" />
815
- <edge from-layer="53" from-port="1" to-layer="54" to-port="0" />
816
- <edge from-layer="54" from-port="1" to-layer="55" to-port="0" />
817
- <edge from-layer="56" from-port="1" to-layer="57" to-port="0" />
818
- </edges>
819
- <rt_info>
820
- <add_attention_mask value="True" />
821
- <add_prefix_space />
822
- <add_special_tokens value="True" />
823
- <bos_token_id value="1" />
824
- <chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
825
- <clean_up_tokenization_spaces />
826
- <detokenizer_input_type value="i64" />
827
- <eos_token_id value="32000" />
828
- <handle_special_tokens_with_re />
829
- <max_length />
830
- <number_of_inputs value="1" />
831
- <openvino_tokenizers_version value="2025.2.0.0-529-cc2fccf72a1" />
832
- <openvino_version value="2025.2.0-18537-69f578c0b73" />
833
- <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;|endoftext|>&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;|endoftext|>&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 1}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {&quot;&lt;s>&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;ids&quot;: [1], &quot;tokens&quot;: [&quot;&lt;s>&quot;]}, &quot;&lt;|endoftext|>&quot;: {&quot;id&quot;: &quot;&lt;|endoftext|>&quot;, &quot;ids&quot;: [32000], &quot;tokens&quot;: [&quot;&lt;|endoftext|>&quot;]}}}" />
834
- <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
835
- <pad_token_id value="32000" />
836
- <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [1, -1, 32000], &quot;type_ids&quot;: [0, 0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [1, -1, 32000, 1, -2, 32000], &quot;type_ids&quot;: [0, 0, 0, 1, 1, 1]}}" />
837
- <sentencepiece_version value="0.2.0" />
838
- <skip_special_tokens value="True" />
839
- <streaming_detokenizer value="False" />
840
- <tokenizer_output_type value="i64" />
841
- <tokenizers_version value="0.21.1" />
842
- <transformers_version value="4.50.0" />
843
- <use_max_padding value="False" />
844
- <use_sentencepiece_backend value="False" />
845
- <utf8_replace_mode value="replace" />
846
- <with_detokenizer value="True" />
847
- </rt_info>
848
- </net>
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_35276" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_35276">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_35282" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_35277" type="StringTensorUnpack" version="opset15">
19
+ <input>
20
+ <port id="0" precision="STRING">
21
+ <dim>-1</dim>
22
+ </port>
23
+ </input>
24
+ <output>
25
+ <port id="1" precision="I32">
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="2" precision="I32">
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="3" precision="U8">
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="ShapeOf_35278" type="ShapeOf" version="opset3">
37
+ <data output_type="i64" />
38
+ <input>
39
+ <port id="0" precision="I32">
40
+ <dim>-1</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I64">
45
+ <dim>1</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Constant_35279" type="Const" version="opset1">
50
+ <data element_type="i64" shape="" offset="0" size="8" />
51
+ <output>
52
+ <port id="0" precision="I64" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_35280" type="Const" version="opset1">
56
+ <data element_type="i64" shape="" offset="0" size="8" />
57
+ <output>
58
+ <port id="0" precision="I64" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_35281" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ <port id="1" precision="I64" />
68
+ <port id="2" precision="I64" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_35283" type="Const" version="opset1">
75
+ <data element_type="i64" shape="" offset="8" size="8" />
76
+ <output>
77
+ <port id="0" precision="I64" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_35284" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I64" />
86
+ </input>
87
+ <output>
88
+ <port id="3" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ </output>
92
+ </layer>
93
+ <layer id="9" name="Constant_35285" type="Const" version="opset1">
94
+ <data element_type="i64" shape="" offset="8" size="8" />
95
+ <output>
96
+ <port id="0" precision="I64" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_35286" type="Const" version="opset1">
100
+ <data element_type="i64" shape="" offset="8" size="8" />
101
+ <output>
102
+ <port id="0" precision="I64" />
103
+ </output>
104
+ </layer>
105
+ <layer id="11" name="Add_35287" type="Add" version="opset1">
106
+ <data auto_broadcast="numpy" />
107
+ <input>
108
+ <port id="0" precision="I64" />
109
+ <port id="1" precision="I64" />
110
+ </input>
111
+ <output>
112
+ <port id="2" precision="I64" />
113
+ </output>
114
+ </layer>
115
+ <layer id="12" name="Constant_35288" type="Const" version="opset1">
116
+ <data element_type="i64" shape="" offset="8" size="8" />
117
+ <output>
118
+ <port id="0" precision="I64" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_35289" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I64" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I64" />
127
+ </input>
128
+ <output>
129
+ <port id="3" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="14" name="Constant_35353" type="Const" version="opset1">
135
+ <data element_type="u8" shape="234" offset="16" size="234" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>234</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_35354" type="SpecialTokensSplit" version="extension">
143
+ <input>
144
+ <port id="0" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="1" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="2" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="3" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="4" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="5" precision="U8">
160
+ <dim>234</dim>
161
+ </port>
162
+ </input>
163
+ <output>
164
+ <port id="6" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="7" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="8" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="9" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="10" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="11" precision="BOOL">
180
+ <dim>-1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="16" name="Constant_35356" type="Const" version="opset1">
185
+ <data element_type="u8" shape="13" offset="250" size="13" />
186
+ <output>
187
+ <port id="0" precision="U8">
188
+ <dim>13</dim>
189
+ </port>
190
+ </output>
191
+ </layer>
192
+ <layer id="17" name="Constant_35358" type="Const" version="opset1">
193
+ <data element_type="u8" shape="5" offset="263" size="5" />
194
+ <output>
195
+ <port id="0" precision="U8">
196
+ <dim>5</dim>
197
+ </port>
198
+ </output>
199
+ </layer>
200
+ <layer id="18" name="RegexNormalization_35359" type="RegexNormalization" version="extension">
201
+ <data global_replace="true" />
202
+ <input>
203
+ <port id="0" precision="I32">
204
+ <dim>-1</dim>
205
+ </port>
206
+ <port id="1" precision="I32">
207
+ <dim>-1</dim>
208
+ </port>
209
+ <port id="2" precision="U8">
210
+ <dim>-1</dim>
211
+ </port>
212
+ <port id="3" precision="BOOL">
213
+ <dim>-1</dim>
214
+ </port>
215
+ <port id="4" precision="U8">
216
+ <dim>13</dim>
217
+ </port>
218
+ <port id="5" precision="U8">
219
+ <dim>5</dim>
220
+ </port>
221
+ </input>
222
+ <output>
223
+ <port id="6" precision="I32">
224
+ <dim>-1</dim>
225
+ </port>
226
+ <port id="7" precision="I32">
227
+ <dim>-1</dim>
228
+ </port>
229
+ <port id="8" precision="U8">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="9" precision="BOOL">
233
+ <dim>-1</dim>
234
+ </port>
235
+ </output>
236
+ </layer>
237
+ <layer id="19" name="Constant_35361" type="Const" version="opset1">
238
+ <data element_type="u8" shape="1" offset="268" size="1" />
239
+ <output>
240
+ <port id="0" precision="U8">
241
+ <dim>1</dim>
242
+ </port>
243
+ </output>
244
+ </layer>
245
+ <layer id="20" name="Constant_35363" type="Const" version="opset1">
246
+ <data element_type="u8" shape="3" offset="269" size="3" />
247
+ <output>
248
+ <port id="0" precision="U8">
249
+ <dim>3</dim>
250
+ </port>
251
+ </output>
252
+ </layer>
253
+ <layer id="21" name="RegexNormalization_35364" type="RegexNormalization" version="extension">
254
+ <data global_replace="true" />
255
+ <input>
256
+ <port id="0" precision="I32">
257
+ <dim>-1</dim>
258
+ </port>
259
+ <port id="1" precision="I32">
260
+ <dim>-1</dim>
261
+ </port>
262
+ <port id="2" precision="U8">
263
+ <dim>-1</dim>
264
+ </port>
265
+ <port id="3" precision="BOOL">
266
+ <dim>-1</dim>
267
+ </port>
268
+ <port id="4" precision="U8">
269
+ <dim>1</dim>
270
+ </port>
271
+ <port id="5" precision="U8">
272
+ <dim>3</dim>
273
+ </port>
274
+ </input>
275
+ <output>
276
+ <port id="6" precision="I32">
277
+ <dim>-1</dim>
278
+ </port>
279
+ <port id="7" precision="I32">
280
+ <dim>-1</dim>
281
+ </port>
282
+ <port id="8" precision="U8">
283
+ <dim>-1</dim>
284
+ </port>
285
+ <port id="9" precision="BOOL">
286
+ <dim>-1</dim>
287
+ </port>
288
+ </output>
289
+ </layer>
290
+ <layer id="22" name="Constant_35366" type="Const" version="opset1">
291
+ <data element_type="i32" shape="32011" offset="272" size="128044" />
292
+ <output>
293
+ <port id="0" precision="I32">
294
+ <dim>32011</dim>
295
+ </port>
296
+ </output>
297
+ </layer>
298
+ <layer id="23" name="Constant_35368" type="Const" version="opset1">
299
+ <data element_type="i32" shape="32011" offset="128316" size="128044" />
300
+ <output>
301
+ <port id="0" precision="I32">
302
+ <dim>32011</dim>
303
+ </port>
304
+ </output>
305
+ </layer>
306
+ <layer id="24" name="Constant_35370" type="Const" version="opset1">
307
+ <data element_type="u8" shape="211066" offset="256360" size="211066" />
308
+ <output>
309
+ <port id="0" precision="U8">
310
+ <dim>211066</dim>
311
+ </port>
312
+ </output>
313
+ </layer>
314
+ <layer id="25" name="Constant_35378" type="Const" version="opset1">
315
+ <data element_type="i32" shape="61249" offset="467426" size="244996" />
316
+ <output>
317
+ <port id="0" precision="I32">
318
+ <dim>61249</dim>
319
+ </port>
320
+ </output>
321
+ </layer>
322
+ <layer id="26" name="Constant_35380" type="Const" version="opset1">
323
+ <data element_type="i32" shape="61249" offset="712422" size="244996" />
324
+ <output>
325
+ <port id="0" precision="I32">
326
+ <dim>61249</dim>
327
+ </port>
328
+ </output>
329
+ </layer>
330
+ <layer id="27" name="Constant_35382" type="Const" version="opset1">
331
+ <data element_type="u8" shape="254123" offset="957418" size="254123" />
332
+ <output>
333
+ <port id="0" precision="U8">
334
+ <dim>254123</dim>
335
+ </port>
336
+ </output>
337
+ </layer>
338
+ <layer id="28" name="Constant_35384" type="Const" version="opset1">
339
+ <data element_type="i32" shape="61249" offset="1211541" size="244996" />
340
+ <output>
341
+ <port id="0" precision="I32">
342
+ <dim>61249</dim>
343
+ </port>
344
+ </output>
345
+ </layer>
346
+ <layer id="29" name="Constant_35386" type="Const" version="opset1">
347
+ <data element_type="i32" shape="61249" offset="1456537" size="244996" />
348
+ <output>
349
+ <port id="0" precision="I32">
350
+ <dim>61249</dim>
351
+ </port>
352
+ </output>
353
+ </layer>
354
+ <layer id="30" name="Constant_35388" type="Const" version="opset1">
355
+ <data element_type="u8" shape="167806" offset="1701533" size="167806" />
356
+ <output>
357
+ <port id="0" precision="U8">
358
+ <dim>167806</dim>
359
+ </port>
360
+ </output>
361
+ </layer>
362
+ <layer id="31" name="Constant_35372" type="Const" version="opset1">
363
+ <data element_type="i32" shape="13" offset="1869339" size="52" />
364
+ <output>
365
+ <port id="0" precision="I32">
366
+ <dim>13</dim>
367
+ </port>
368
+ </output>
369
+ </layer>
370
+ <layer id="32" name="Constant_35374" type="Const" version="opset1">
371
+ <data element_type="i32" shape="13" offset="1869391" size="52" />
372
+ <output>
373
+ <port id="0" precision="I32">
374
+ <dim>13</dim>
375
+ </port>
376
+ </output>
377
+ </layer>
378
+ <layer id="33" name="Constant_35376" type="Const" version="opset1">
379
+ <data element_type="u8" shape="154" offset="1869443" size="154" />
380
+ <output>
381
+ <port id="0" precision="U8">
382
+ <dim>154</dim>
383
+ </port>
384
+ </output>
385
+ </layer>
386
+ <layer id="34" name="Constant_35389" type="Const" version="opset1">
387
+ <data element_type="i32" shape="13" offset="1869597" size="52" />
388
+ <output>
389
+ <port id="0" precision="I32">
390
+ <dim>13</dim>
391
+ </port>
392
+ </output>
393
+ </layer>
394
+ <layer id="35" name="BPETokenizer_35390" type="BPETokenizer" version="extension">
395
+ <data unk_token="&lt;unk>" fuse_unk="true" suffix_indicator="" end_suffix="" byte_fallback="true" cache_capacity="20000" />
396
+ <input>
397
+ <port id="0" precision="I32">
398
+ <dim>-1</dim>
399
+ </port>
400
+ <port id="1" precision="I32">
401
+ <dim>-1</dim>
402
+ </port>
403
+ <port id="2" precision="I32">
404
+ <dim>-1</dim>
405
+ </port>
406
+ <port id="3" precision="I32">
407
+ <dim>-1</dim>
408
+ </port>
409
+ <port id="4" precision="U8">
410
+ <dim>-1</dim>
411
+ </port>
412
+ <port id="5" precision="I32">
413
+ <dim>32011</dim>
414
+ </port>
415
+ <port id="6" precision="I32">
416
+ <dim>32011</dim>
417
+ </port>
418
+ <port id="7" precision="U8">
419
+ <dim>211066</dim>
420
+ </port>
421
+ <port id="8" precision="I32">
422
+ <dim>61249</dim>
423
+ </port>
424
+ <port id="9" precision="I32">
425
+ <dim>61249</dim>
426
+ </port>
427
+ <port id="10" precision="U8">
428
+ <dim>254123</dim>
429
+ </port>
430
+ <port id="11" precision="I32">
431
+ <dim>61249</dim>
432
+ </port>
433
+ <port id="12" precision="I32">
434
+ <dim>61249</dim>
435
+ </port>
436
+ <port id="13" precision="U8">
437
+ <dim>167806</dim>
438
+ </port>
439
+ <port id="14" precision="I32">
440
+ <dim>13</dim>
441
+ </port>
442
+ <port id="15" precision="I32">
443
+ <dim>13</dim>
444
+ </port>
445
+ <port id="16" precision="U8">
446
+ <dim>154</dim>
447
+ </port>
448
+ <port id="17" precision="I32">
449
+ <dim>13</dim>
450
+ </port>
451
+ </input>
452
+ <output>
453
+ <port id="18" precision="I32">
454
+ <dim>-1</dim>
455
+ </port>
456
+ <port id="19" precision="I32">
457
+ <dim>-1</dim>
458
+ </port>
459
+ <port id="20" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ </output>
463
+ </layer>
464
+ <layer id="36" name="Constant_35391" type="Const" version="opset1">
465
+ <data element_type="i32" shape="" offset="1869649" size="4" />
466
+ <output>
467
+ <port id="0" precision="I32" />
468
+ </output>
469
+ </layer>
470
+ <layer id="37" name="Constant_35393" type="Const" version="opset1">
471
+ <data element_type="u8" shape="4" offset="1869653" size="4" />
472
+ <output>
473
+ <port id="0" precision="U8">
474
+ <dim>4</dim>
475
+ </port>
476
+ </output>
477
+ </layer>
478
+ <layer id="38" name="Constant_35395" type="Const" version="opset1">
479
+ <data element_type="u8" shape="13" offset="1869657" size="13" />
480
+ <output>
481
+ <port id="0" precision="U8">
482
+ <dim>13</dim>
483
+ </port>
484
+ </output>
485
+ </layer>
486
+ <layer id="39" name="Truncate_35396" type="Truncate" version="extension">
487
+ <data m_num_inputs="1" />
488
+ <input>
489
+ <port id="0" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="1" precision="I32">
493
+ <dim>-1</dim>
494
+ </port>
495
+ <port id="2" precision="I32">
496
+ <dim>-1</dim>
497
+ </port>
498
+ <port id="3" precision="I32" />
499
+ <port id="4" precision="U8">
500
+ <dim>4</dim>
501
+ </port>
502
+ <port id="5" precision="U8">
503
+ <dim>13</dim>
504
+ </port>
505
+ </input>
506
+ <output>
507
+ <port id="6" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ <port id="7" precision="I32">
511
+ <dim>-1</dim>
512
+ </port>
513
+ <port id="8" precision="I32">
514
+ <dim>-1</dim>
515
+ </port>
516
+ </output>
517
+ </layer>
518
+ <layer id="40" name="Constant_35397" type="Const" version="opset1">
519
+ <data element_type="i32" shape="1" offset="1869670" size="4" />
520
+ <output>
521
+ <port id="0" precision="I32">
522
+ <dim>1</dim>
523
+ </port>
524
+ </output>
525
+ </layer>
526
+ <layer id="41" name="CombineSegments_35398" type="CombineSegments" version="extension">
527
+ <input>
528
+ <port id="0" precision="I32">
529
+ <dim>-1</dim>
530
+ </port>
531
+ <port id="1" precision="I32">
532
+ <dim>-1</dim>
533
+ </port>
534
+ <port id="2" precision="I32">
535
+ <dim>-1</dim>
536
+ </port>
537
+ <port id="3" precision="I32">
538
+ <dim>1</dim>
539
+ </port>
540
+ </input>
541
+ <output>
542
+ <port id="4" precision="I32">
543
+ <dim>-1</dim>
544
+ </port>
545
+ <port id="5" precision="I32">
546
+ <dim>-1</dim>
547
+ </port>
548
+ <port id="6" precision="I32">
549
+ <dim>-1</dim>
550
+ </port>
551
+ <port id="7" precision="I32">
552
+ <dim>-1</dim>
553
+ </port>
554
+ <port id="8" precision="I32">
555
+ <dim>-1</dim>
556
+ </port>
557
+ <port id="9" precision="I32">
558
+ <dim>-1</dim>
559
+ </port>
560
+ </output>
561
+ </layer>
562
+ <layer id="42" name="Subtract_35399" type="Subtract" version="opset1">
563
+ <data auto_broadcast="numpy" />
564
+ <input>
565
+ <port id="0" precision="I32">
566
+ <dim>-1</dim>
567
+ </port>
568
+ <port id="1" precision="I32">
569
+ <dim>-1</dim>
570
+ </port>
571
+ </input>
572
+ <output>
573
+ <port id="2" precision="I32">
574
+ <dim>-1</dim>
575
+ </port>
576
+ </output>
577
+ </layer>
578
+ <layer id="43" name="Constant_35400" type="Const" version="opset1">
579
+ <data element_type="i32" shape="" offset="1869670" size="4" />
580
+ <output>
581
+ <port id="0" precision="I32" />
582
+ </output>
583
+ </layer>
584
+ <layer id="44" name="ReduceMax_35401" type="ReduceMax" version="opset1">
585
+ <data keep_dims="false" />
586
+ <input>
587
+ <port id="0" precision="I32">
588
+ <dim>-1</dim>
589
+ </port>
590
+ <port id="1" precision="I32" />
591
+ </input>
592
+ <output>
593
+ <port id="2" precision="I32" />
594
+ </output>
595
+ </layer>
596
+ <layer id="45" name="Constant_35402" type="Const" version="opset1">
597
+ <data element_type="i32" shape="" offset="1869674" size="4" />
598
+ <output>
599
+ <port id="0" precision="I32" />
600
+ </output>
601
+ </layer>
602
+ <layer id="46" name="RaggedToDense_35403" type="RaggedToDense" version="extension">
603
+ <data pad_right="false" m_pad_max_length="false" />
604
+ <input>
605
+ <port id="0" precision="I32">
606
+ <dim>-1</dim>
607
+ </port>
608
+ <port id="1" precision="I32">
609
+ <dim>-1</dim>
610
+ </port>
611
+ <port id="2" precision="I32">
612
+ <dim>-1</dim>
613
+ </port>
614
+ <port id="3" precision="I32" />
615
+ <port id="4" precision="I32" />
616
+ </input>
617
+ <output>
618
+ <port id="5" precision="I32">
619
+ <dim>-1</dim>
620
+ <dim>-1</dim>
621
+ </port>
622
+ <port id="6" precision="BOOL">
623
+ <dim>-1</dim>
624
+ <dim>-1</dim>
625
+ </port>
626
+ </output>
627
+ </layer>
628
+ <layer id="47" name="Convert_35404" type="Convert" version="opset1">
629
+ <data destination_type="i32" />
630
+ <input>
631
+ <port id="0" precision="BOOL">
632
+ <dim>-1</dim>
633
+ <dim>-1</dim>
634
+ </port>
635
+ </input>
636
+ <output>
637
+ <port id="1" precision="I32">
638
+ <dim>-1</dim>
639
+ <dim>-1</dim>
640
+ </port>
641
+ </output>
642
+ </layer>
643
+ <layer id="48" name="Convert_35404.0" type="Convert" version="opset1">
644
+ <data destination_type="i64" />
645
+ <input>
646
+ <port id="0" precision="I32">
647
+ <dim>-1</dim>
648
+ <dim>-1</dim>
649
+ </port>
650
+ </input>
651
+ <output>
652
+ <port id="1" precision="I64" names="attention_mask">
653
+ <dim>-1</dim>
654
+ <dim>-1</dim>
655
+ </port>
656
+ </output>
657
+ </layer>
658
+ <layer id="50" name="RaggedToDense_35403.0" 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="input_ids">
668
+ <dim>-1</dim>
669
+ <dim>-1</dim>
670
+ </port>
671
+ </output>
672
+ </layer>
673
+ <layer id="51" name="Result_35407" type="Result" version="opset1" output_names="input_ids">
674
+ <input>
675
+ <port id="0" precision="I64">
676
+ <dim>-1</dim>
677
+ <dim>-1</dim>
678
+ </port>
679
+ </input>
680
+ </layer>
681
+ <layer id="49" name="Result_35409" type="Result" version="opset1" output_names="attention_mask">
682
+ <input>
683
+ <port id="0" precision="I64">
684
+ <dim>-1</dim>
685
+ <dim>-1</dim>
686
+ </port>
687
+ </input>
688
+ </layer>
689
+ </layers>
690
+ <edges>
691
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
692
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
693
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
694
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
695
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
696
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
697
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
698
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
699
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
700
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
701
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
702
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
703
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
704
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
705
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
706
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
707
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
708
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
709
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
710
+ <edge from-layer="15" from-port="10" to-layer="18" to-port="2" />
711
+ <edge from-layer="15" from-port="7" to-layer="35" to-port="1" />
712
+ <edge from-layer="15" from-port="6" to-layer="35" to-port="0" />
713
+ <edge from-layer="15" from-port="11" to-layer="18" to-port="3" />
714
+ <edge from-layer="15" from-port="9" to-layer="18" to-port="1" />
715
+ <edge from-layer="15" from-port="8" to-layer="18" to-port="0" />
716
+ <edge from-layer="16" from-port="0" to-layer="18" to-port="4" />
717
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
718
+ <edge from-layer="18" from-port="6" to-layer="21" to-port="0" />
719
+ <edge from-layer="18" from-port="7" to-layer="21" to-port="1" />
720
+ <edge from-layer="18" from-port="8" to-layer="21" to-port="2" />
721
+ <edge from-layer="18" from-port="9" to-layer="21" to-port="3" />
722
+ <edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
723
+ <edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
724
+ <edge from-layer="21" from-port="6" to-layer="35" to-port="2" />
725
+ <edge from-layer="21" from-port="7" to-layer="35" to-port="3" />
726
+ <edge from-layer="21" from-port="8" to-layer="35" to-port="4" />
727
+ <edge from-layer="22" from-port="0" to-layer="35" to-port="5" />
728
+ <edge from-layer="23" from-port="0" to-layer="35" to-port="6" />
729
+ <edge from-layer="24" from-port="0" to-layer="35" to-port="7" />
730
+ <edge from-layer="25" from-port="0" to-layer="35" to-port="8" />
731
+ <edge from-layer="26" from-port="0" to-layer="35" to-port="9" />
732
+ <edge from-layer="27" from-port="0" to-layer="35" to-port="10" />
733
+ <edge from-layer="28" from-port="0" to-layer="35" to-port="11" />
734
+ <edge from-layer="29" from-port="0" to-layer="35" to-port="12" />
735
+ <edge from-layer="30" from-port="0" to-layer="35" to-port="13" />
736
+ <edge from-layer="31" from-port="0" to-layer="35" to-port="14" />
737
+ <edge from-layer="32" from-port="0" to-layer="35" to-port="15" />
738
+ <edge from-layer="33" from-port="0" to-layer="35" to-port="16" />
739
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="17" />
740
+ <edge from-layer="35" from-port="18" to-layer="39" to-port="0" />
741
+ <edge from-layer="35" from-port="19" to-layer="39" to-port="1" />
742
+ <edge from-layer="35" from-port="20" to-layer="39" to-port="2" />
743
+ <edge from-layer="36" from-port="0" to-layer="39" to-port="3" />
744
+ <edge from-layer="37" from-port="0" to-layer="39" to-port="4" />
745
+ <edge from-layer="38" from-port="0" to-layer="39" to-port="5" />
746
+ <edge from-layer="39" from-port="6" to-layer="41" to-port="0" />
747
+ <edge from-layer="39" from-port="8" to-layer="41" to-port="2" />
748
+ <edge from-layer="39" from-port="7" to-layer="41" to-port="1" />
749
+ <edge from-layer="40" from-port="0" to-layer="41" to-port="3" />
750
+ <edge from-layer="41" from-port="5" to-layer="42" to-port="0" />
751
+ <edge from-layer="41" from-port="4" to-layer="42" to-port="1" />
752
+ <edge from-layer="41" from-port="4" to-layer="46" to-port="0" />
753
+ <edge from-layer="41" from-port="5" to-layer="46" to-port="1" />
754
+ <edge from-layer="41" from-port="6" to-layer="46" to-port="2" />
755
+ <edge from-layer="42" from-port="2" to-layer="44" to-port="0" />
756
+ <edge from-layer="43" from-port="0" to-layer="44" to-port="1" />
757
+ <edge from-layer="44" from-port="2" to-layer="46" to-port="3" />
758
+ <edge from-layer="45" from-port="0" to-layer="46" to-port="4" />
759
+ <edge from-layer="46" from-port="6" to-layer="47" to-port="0" />
760
+ <edge from-layer="46" from-port="5" to-layer="50" to-port="0" />
761
+ <edge from-layer="47" from-port="1" to-layer="48" to-port="0" />
762
+ <edge from-layer="48" from-port="1" to-layer="49" to-port="0" />
763
+ <edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
764
+ </edges>
765
+ <rt_info>
766
+ <add_attention_mask value="True" />
767
+ <add_prefix_space />
768
+ <add_special_tokens value="True" />
769
+ <bos_token_id value="1" />
770
+ <chat_template value="{% for message in messages %}{% if message['role'] == 'system' %}{{'&lt;|system|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'user' %}{{'&lt;|user|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% elif message['role'] == 'assistant' %}{{'&lt;|assistant|>&#10;' + message['content'] + '&lt;|end|>&#10;'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|assistant|>&#10;' }}{% else %}{{ eos_token }}{% endif %}" />
771
+ <clean_up_tokenization_spaces />
772
+ <detokenizer_input_type value="i64" />
773
+ <eos_token_id value="32000" />
774
+ <handle_special_tokens_with_re />
775
+ <max_length />
776
+ <number_of_inputs value="1" />
777
+ <openvino_tokenizers_version value="2025.4.0.0-615-c8aad078405" />
778
+ <openvino_version value="2025.4.0-20104-e6264070ff2" />
779
+ <original_post_processor_template value="{&quot;type&quot;: &quot;TemplateProcessing&quot;, &quot;single&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}], &quot;pair&quot;: [{&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&quot;, &quot;type_id&quot;: 1}}], &quot;special_tokens&quot;: {}}" />
780
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
781
+ <pad_token_id value="32000" />
782
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 1]}}" />
783
+ <skip_special_tokens value="True" />
784
+ <streaming_detokenizer value="False" />
785
+ <tokenizer_output_type value="i64" />
786
+ <tokenizers_version value="0.21.4" />
787
+ <transformers_version value="4.53.3" />
788
+ <use_max_padding value="False" />
789
+ <use_sentencepiece_backend value="False" />
790
+ <utf8_replace_mode value="replace" />
791
+ <with_detokenizer value="True" />
792
+ </rt_info>
793
+ </net>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json CHANGED
@@ -1,30 +1,30 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json CHANGED
@@ -150,83 +150,28 @@
150
  "post_processor": {
151
  "type": "TemplateProcessing",
152
  "single": [
153
- {
154
- "SpecialToken": {
155
- "id": "<s>",
156
- "type_id": 0
157
- }
158
- },
159
  {
160
  "Sequence": {
161
  "id": "A",
162
  "type_id": 0
163
  }
164
- },
165
- {
166
- "SpecialToken": {
167
- "id": "<|endoftext|>",
168
- "type_id": 0
169
- }
170
  }
171
  ],
172
  "pair": [
173
- {
174
- "SpecialToken": {
175
- "id": "<s>",
176
- "type_id": 0
177
- }
178
- },
179
  {
180
  "Sequence": {
181
  "id": "A",
182
  "type_id": 0
183
  }
184
  },
185
- {
186
- "SpecialToken": {
187
- "id": "<|endoftext|>",
188
- "type_id": 0
189
- }
190
- },
191
- {
192
- "SpecialToken": {
193
- "id": "<s>",
194
- "type_id": 1
195
- }
196
- },
197
  {
198
  "Sequence": {
199
  "id": "B",
200
  "type_id": 1
201
  }
202
- },
203
- {
204
- "SpecialToken": {
205
- "id": "<|endoftext|>",
206
- "type_id": 1
207
- }
208
  }
209
  ],
210
- "special_tokens": {
211
- "<s>": {
212
- "id": "<s>",
213
- "ids": [
214
- 1
215
- ],
216
- "tokens": [
217
- "<s>"
218
- ]
219
- },
220
- "<|endoftext|>": {
221
- "id": "<|endoftext|>",
222
- "ids": [
223
- 32000
224
- ],
225
- "tokens": [
226
- "<|endoftext|>"
227
- ]
228
- }
229
- }
230
  },
231
  "decoder": {
232
  "type": "Sequence",
 
150
  "post_processor": {
151
  "type": "TemplateProcessing",
152
  "single": [
 
 
 
 
 
 
153
  {
154
  "Sequence": {
155
  "id": "A",
156
  "type_id": 0
157
  }
 
 
 
 
 
 
158
  }
159
  ],
160
  "pair": [
 
 
 
 
 
 
161
  {
162
  "Sequence": {
163
  "id": "A",
164
  "type_id": 0
165
  }
166
  },
 
 
 
 
 
 
 
 
 
 
 
 
167
  {
168
  "Sequence": {
169
  "id": "B",
170
  "type_id": 1
171
  }
 
 
 
 
 
 
172
  }
173
  ],
174
+ "special_tokens": {}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
175
  },
176
  "decoder": {
177
  "type": "Sequence",
tokenizer_config.json CHANGED
@@ -1,132 +1,131 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": true,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": true,
27
- "single_word": false,
28
- "special": false
29
- },
30
- "32000": {
31
- "content": "<|endoftext|>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": true
37
- },
38
- "32001": {
39
- "content": "<|assistant|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": true,
43
- "single_word": false,
44
- "special": true
45
- },
46
- "32002": {
47
- "content": "<|placeholder1|>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": true,
51
- "single_word": false,
52
- "special": true
53
- },
54
- "32003": {
55
- "content": "<|placeholder2|>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": true,
59
- "single_word": false,
60
- "special": true
61
- },
62
- "32004": {
63
- "content": "<|placeholder3|>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": true,
67
- "single_word": false,
68
- "special": true
69
- },
70
- "32005": {
71
- "content": "<|placeholder4|>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": true,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "32006": {
79
- "content": "<|system|>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": true,
83
- "single_word": false,
84
- "special": true
85
- },
86
- "32007": {
87
- "content": "<|end|>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": true,
91
- "single_word": false,
92
- "special": true
93
- },
94
- "32008": {
95
- "content": "<|placeholder5|>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": true,
99
- "single_word": false,
100
- "special": true
101
- },
102
- "32009": {
103
- "content": "<|placeholder6|>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": true,
107
- "single_word": false,
108
- "special": true
109
- },
110
- "32010": {
111
- "content": "<|user|>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": true,
115
- "single_word": false,
116
- "special": true
117
- }
118
- },
119
- "bos_token": "<s>",
120
- "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
- "clean_up_tokenization_spaces": false,
122
- "eos_token": "<|endoftext|>",
123
- "extra_special_tokens": {},
124
- "legacy": false,
125
- "model_max_length": 4096,
126
- "pad_token": "<|endoftext|>",
127
- "padding_side": "right",
128
- "sp_model_kwargs": {},
129
- "tokenizer_class": "LlamaTokenizer",
130
- "unk_token": "<unk>",
131
- "use_default_system_prompt": false
132
- }
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "extra_special_tokens": {},
123
+ "legacy": false,
124
+ "model_max_length": 4096,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }