Hugging Face's logo

OpenVINO
/
TinyLlama-1.1B-Chat-v1.0-int4-ov

Text Generation
Transformers
OpenVINO
llama
conversational
Model card Files
xet
Community
1
openvino-ci commited on
Commit
5ba4157
·
verified ·
1 Parent(s): 7db6067

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. chat_template.jinja +15 -0
  2. config.json +3 -2
  3. generation_config.json +7 -0
  4. openvino_detokenizer.bin +2 -2
  5. openvino_detokenizer.xml +278 -22
  6. openvino_model.bin +2 -2
  7. openvino_model.xml +0 -0
  8. openvino_tokenizer.bin +2 -2
  9. openvino_tokenizer.xml +666 -74
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +2 -1
chat_template.jinja ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}
2
+ {% if message['role'] == 'user' %}
3
+ {{ '<|user|>
4
+ ' + message['content'] + eos_token }}
5
+ {% elif message['role'] == 'system' %}
6
+ {{ '<|system|>
7
+ ' + message['content'] + eos_token }}
8
+ {% elif message['role'] == 'assistant' %}
9
+ {{ '<|assistant|>
10
+ ' + message['content'] + eos_token }}
11
+ {% endif %}
12
+ {% if loop.last and add_generation_prompt %}
13
+ {{ '<|assistant|>' }}
14
+ {% endif %}
15
+ {% endfor %}
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -7,11 +6,13 @@
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 5632,
14
  "max_position_embeddings": 2048,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 22,
@@ -22,7 +23,7 @@
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.40.1",
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
 
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 64,
10
  "hidden_act": "silu",
11
  "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 5632,
14
  "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 22,
 
23
  "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.55.4",
27
  "use_cache": true,
28
  "vocab_size": 32000
29
  }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.55.4"
7
+ }
openvino_detokenizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9556d0a1f310629e217450ac4198c49f5457f1a69e22ce7c9f8e81fab4d530a7
3
- size 499723
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e56641fb954a24eee40d3960dd259e529633371718e6c2166a6c69e61e83ba7
3
+ size 466938
openvino_detokenizer.xml CHANGED
@@ -1,62 +1,268 @@
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
- <layer id="0" name="Parameter_22" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
- <port id="0" precision="I64" names="Parameter_22">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
- <layer id="1" name="Constant_2" type="Const" version="opset1">
14
- <data element_type="u8" shape="499723" offset="0" size="499723" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  <output>
16
  <port id="0" precision="U8">
17
- <dim>499723</dim>
18
  </port>
19
  </output>
20
  </layer>
21
- <layer id="2" name="Convert_32" type="Convert" version="opset1">
22
- <data destination_type="i32" />
 
 
 
 
 
 
 
 
23
  <input>
24
- <port id="0" precision="I64">
25
  <dim>-1</dim>
26
  <dim>-1</dim>
27
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
28
  </input>
29
  <output>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  <port id="1" precision="I32">
31
  <dim>-1</dim>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  <dim>-1</dim>
33
  </port>
34
  </output>
35
  </layer>
36
- <layer id="3" name="SentencepieceDetokenizer_23" type="SentencepieceDetokenizer" version="extension">
37
  <input>
38
- <port id="0" precision="U8">
39
- <dim>499723</dim>
40
  </port>
41
  <port id="1" precision="I32">
42
  <dim>-1</dim>
 
 
43
  <dim>-1</dim>
44
  </port>
45
  </input>
46
  <output>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  <port id="2" precision="I32">
48
  <dim>-1</dim>
49
  </port>
50
  <port id="3" precision="I32">
51
  <dim>-1</dim>
52
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  <port id="4" precision="U8">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  <dim>-1</dim>
55
  </port>
56
  </output>
57
  </layer>
58
- <layer id="4" name="StringTensorPack_24" type="StringTensorPack" version="extension">
59
- <data mode="begins_ends" />
60
  <input>
61
  <port id="0" precision="I32">
62
  <dim>-1</dim>
@@ -69,12 +275,12 @@
69
  </port>
70
  </input>
71
  <output>
72
- <port id="3" precision="STRING" names="string_output">
73
  <dim>-1</dim>
74
  </port>
75
  </output>
76
  </layer>
77
- <layer id="5" name="Result_25" type="Result" version="opset1">
78
  <input>
79
  <port id="0" precision="STRING">
80
  <dim>-1</dim>
@@ -83,15 +289,65 @@
83
  </layer>
84
  </layers>
85
  <edges>
86
- <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
87
- <edge from-layer="1" from-port="0" to-layer="3" to-port="0" />
88
- <edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
89
- <edge from-layer="3" from-port="2" to-layer="4" to-port="0" />
90
- <edge from-layer="3" from-port="3" to-layer="4" to-port="1" />
91
- <edge from-layer="3" from-port="4" to-layer="4" to-port="2" />
92
- <edge from-layer="4" from-port="3" to-layer="5" to-port="0" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93
  </edges>
94
  <rt_info>
 
 
 
 
 
 
 
95
  <eos_token_id value="2" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  </rt_info>
97
  </net>
 
1
  <?xml version="1.0"?>
2
  <net name="detokenizer" version="11">
3
  <layers>
4
+ <layer id="0" name="Parameter_70751" type="Parameter" version="opset1">
5
  <data shape="?,?" element_type="i64" />
6
  <output>
7
+ <port id="0" precision="I64" names="Parameter_70751">
8
  <dim>-1</dim>
9
  <dim>-1</dim>
10
  </port>
11
  </output>
12
  </layer>
13
+ <layer id="1" name="Convert_70955" 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_70704" type="Const" version="opset1">
29
+ <data element_type="i32" shape="32000" offset="0" size="128000" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>32000</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_70706" type="Const" version="opset1">
37
+ <data element_type="i32" shape="32000" offset="128000" size="128000" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>32000</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_70708" type="Const" version="opset1">
45
+ <data element_type="u8" shape="210919" offset="256000" size="210919" />
46
  <output>
47
  <port id="0" precision="U8">
48
+ <dim>210919</dim>
49
  </port>
50
  </output>
51
  </layer>
52
+ <layer id="5" name="Slice_70756" type="Const" version="opset1">
53
+ <data element_type="i32" shape="3" offset="466919" size="12" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>3</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_70758" 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>32000</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>32000</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>210919</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>3</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_70760" type="Const" version="opset1">
99
+ <data element_type="u8" shape="3" offset="466931" 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_70762" type="Const" version="opset1">
107
+ <data element_type="u8" shape="1" offset="466934" 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_70763" 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_70764" 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_70765" 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_70767" type="Const" version="opset1">
194
+ <data element_type="u8" shape="2" offset="466935" 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_70769" type="Const" version="opset1">
202
+ <data element_type="u8" shape="0" offset="466937" 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_70770" 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_70771" 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_70772" type="StringTensorPack" version="opset15">
 
266
  <input>
267
  <port id="0" precision="I32">
268
  <dim>-1</dim>
 
275
  </port>
276
  </input>
277
  <output>
278
+ <port id="3" precision="STRING" names="Result_70773,string_output">
279
  <dim>-1</dim>
280
  </port>
281
  </output>
282
  </layer>
283
+ <layer id="17" name="Result_70773" type="Result" version="opset1" output_names="Result_70773,string_output">
284
  <input>
285
  <port id="0" precision="STRING">
286
  <dim>-1</dim>
 
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 %}&#10;{% if message['role'] == 'user' %}&#10;{{ '&lt;|user|>&#10;' + message['content'] + eos_token }}&#10;{% elif message['role'] == 'system' %}&#10;{{ '&lt;|system|>&#10;' + message['content'] + eos_token }}&#10;{% elif message['role'] == 'assistant' %}&#10;{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token }}&#10;{% endif %}&#10;{% if loop.last and add_generation_prompt %}&#10;{{ '&lt;|assistant|>' }}&#10;{% endif %}&#10;{% endfor %}" />
329
+ <clean_up_tokenization_spaces />
330
+ <detokenizer_input_type value="i64" />
331
  <eos_token_id value="2" />
332
+ <handle_special_tokens_with_re />
333
+ <max_length />
334
+ <number_of_inputs value="1" />
335
+ <openvino_tokenizers_version value="2025.4.0.0-625-3694f87878e" />
336
+ <openvino_version value="2025.4.0-20398-7a975177ff4-releases/2025/4" />
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;pair&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 1}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&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;]}}}" />
338
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
339
+ <pad_token_id value="2" />
340
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [1, -1], &quot;type_ids&quot;: [0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [1, -1, 1, -2], &quot;type_ids&quot;: [0, 0, 1, 1]}}" />
341
+ <sentencepiece_version value="0.2.1" />
342
+ <skip_special_tokens value="True" />
343
+ <streaming_detokenizer value="False" />
344
+ <tiktoken_version value="0.12.0" />
345
+ <tokenizer_output_type value="i64" />
346
+ <tokenizers_version value="0.21.4" />
347
+ <transformers_version value="4.55.4" />
348
+ <use_max_padding value="False" />
349
+ <use_sentencepiece_backend value="False" />
350
+ <utf8_replace_mode value="replace" />
351
+ <with_detokenizer value="True" />
352
  </rt_info>
353
  </net>
openvino_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:818fb66c94a423670adf67567472c6fe233452e3e6b5d89dba35dbe3b5b29287
3
- size 631029685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3776f4c54c1af5e5c4b95b6f3e62b381847e081e0d13bea3daa8f2849387cb2d
3
+ size 631214037
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 sha256:198c98ed1f62d49eace27a191b19b0ddec76566ca0b2ff88806b67ae1702c20f
3
- size 499735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab2cc7fc62a4809d4beb361267f58902be22bf0d38b4cb33db3fee196c7cfdd
3
+ size 1868957
openvino_tokenizer.xml CHANGED
@@ -1,178 +1,686 @@
1
  <?xml version="1.0"?>
2
  <net name="tokenizer" version="11">
3
  <layers>
4
- <layer id="0" name="string_input" type="Parameter" version="opset1">
5
  <data shape="?" element_type="string" />
6
  <output>
7
- <port id="0" precision="STRING" names="string_input">
8
  <dim>-1</dim>
9
  </port>
10
  </output>
11
  </layer>
12
- <layer id="1" name="Constant_8" 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_1" type="Const" version="opset1">
19
- <data element_type="u8" shape="499723" offset="4" size="499723" />
20
  <output>
21
- <port id="0" precision="U8">
22
- <dim>499723</dim>
 
 
 
 
 
 
23
  </port>
24
  </output>
25
  </layer>
26
- <layer id="3" name="SentencepieceTokenizer_4" type="SentencepieceTokenizer" version="extension">
27
- <data nbest_size="0" alpha="0" add_bos="true" add_eos="false" reverse="false" />
 
 
 
 
 
28
  <input>
29
- <port id="0" precision="U8">
30
- <dim>499723</dim>
31
- </port>
32
- <port id="1" precision="STRING">
33
  <dim>-1</dim>
34
  </port>
35
  </input>
36
  <output>
37
- <port id="2" precision="I64">
38
  <dim>-1</dim>
39
- <dim>2</dim>
40
  </port>
41
- <port id="3" precision="I32">
42
  <dim>-1</dim>
43
  </port>
44
- <port id="4" precision="I64">
45
- <dim>2</dim>
46
  </port>
47
  </output>
48
  </layer>
49
- <layer id="4" name="Broadcast_9" type="Broadcast" version="opset3">
50
- <data mode="numpy" />
51
  <input>
52
- <port id="0" precision="I32" />
 
 
 
 
53
  <port id="1" precision="I64">
54
- <dim>2</dim>
55
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  </input>
57
  <output>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  <port id="2" precision="I32">
59
  <dim>-1</dim>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
  <dim>-1</dim>
61
  </port>
62
  </output>
63
  </layer>
64
- <layer id="5" name="Constant_10" type="Const" version="opset1">
65
- <data element_type="i32" shape="" offset="499727" size="4" />
66
  <output>
67
- <port id="0" precision="I32" />
 
 
68
  </output>
69
  </layer>
70
- <layer id="6" name="ShapeOf_11" type="ShapeOf" version="opset3">
71
- <data output_type="i64" />
 
 
 
 
 
 
 
 
72
  <input>
73
  <port id="0" precision="I32">
74
  <dim>-1</dim>
75
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  </input>
77
  <output>
78
- <port id="1" precision="I64">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  <dim>1</dim>
80
  </port>
81
  </output>
82
  </layer>
83
- <layer id="7" name="Broadcast_12" type="Broadcast" version="opset3">
84
- <data mode="numpy" />
 
 
 
 
 
 
 
 
85
  <input>
86
- <port id="0" precision="I32" />
87
- <port id="1" precision="I64">
 
 
 
 
 
 
 
 
 
 
 
88
  <dim>1</dim>
89
  </port>
 
 
 
90
  </input>
91
  <output>
92
- <port id="2" precision="I32">
 
 
 
 
 
 
93
  <dim>-1</dim>
94
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  </output>
96
  </layer>
97
- <layer id="8" name="ScatterNDUpdate_16" type="ScatterNDUpdate" version="opset4">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  <input>
99
  <port id="0" precision="I32">
100
  <dim>-1</dim>
101
- <dim>-1</dim>
102
  </port>
103
- <port id="1" precision="I64">
104
  <dim>-1</dim>
105
- <dim>2</dim>
106
  </port>
107
  <port id="2" precision="I32">
108
  <dim>-1</dim>
109
  </port>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
  </input>
111
  <output>
112
- <port id="3" precision="I32">
113
  <dim>-1</dim>
 
 
 
 
 
114
  <dim>-1</dim>
115
  </port>
116
  </output>
117
  </layer>
118
- <layer id="9" name="ScatterNDUpdate_16" type="Convert" version="opset1">
119
- <data destination_type="i64" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
120
  <input>
121
  <port id="0" precision="I32">
122
  <dim>-1</dim>
 
 
123
  <dim>-1</dim>
124
  </port>
 
 
 
 
 
 
 
 
 
 
125
  </input>
126
  <output>
127
- <port id="1" precision="I64" names="attention_mask">
 
 
 
128
  <dim>-1</dim>
 
 
129
  <dim>-1</dim>
130
  </port>
131
  </output>
132
  </layer>
133
- <layer id="11" name="Constant_5" type="Const" version="opset1">
134
- <data element_type="i32" shape="" offset="499731" size="4" />
135
  <output>
136
- <port id="0" precision="I32" />
 
 
137
  </output>
138
  </layer>
139
- <layer id="12" name="Broadcast_6" type="Broadcast" version="opset3">
140
- <data mode="numpy" />
141
  <input>
142
  <port id="0" precision="I32" />
143
- <port id="1" precision="I64">
 
 
 
 
 
 
 
 
 
 
 
 
 
144
  <dim>2</dim>
145
  </port>
146
  </input>
147
  <output>
148
- <port id="2" precision="I32">
149
  <dim>-1</dim>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  <dim>-1</dim>
151
  </port>
152
  </output>
153
  </layer>
154
- <layer id="13" name="ScatterNDUpdate_7" type="ScatterNDUpdate" version="opset4">
 
155
  <input>
156
  <port id="0" precision="I32">
157
  <dim>-1</dim>
 
 
158
  <dim>-1</dim>
159
  </port>
160
- <port id="1" precision="I64">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
161
  <dim>-1</dim>
162
- <dim>2</dim>
163
  </port>
164
  <port id="2" precision="I32">
165
  <dim>-1</dim>
166
  </port>
 
 
167
  </input>
168
  <output>
169
- <port id="3" precision="I32">
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
170
  <dim>-1</dim>
171
  <dim>-1</dim>
172
  </port>
173
  </output>
174
  </layer>
175
- <layer id="14" name="ScatterNDUpdate_7" type="Convert" version="opset1">
176
  <data destination_type="i64" />
177
  <input>
178
  <port id="0" precision="I32">
@@ -187,7 +695,7 @@
187
  </port>
188
  </output>
189
  </layer>
190
- <layer id="15" name="Result_17" type="Result" version="opset1">
191
  <input>
192
  <port id="0" precision="I64">
193
  <dim>-1</dim>
@@ -195,7 +703,7 @@
195
  </port>
196
  </input>
197
  </layer>
198
- <layer id="10" name="Result_18" type="Result" version="opset1">
199
  <input>
200
  <port id="0" precision="I64">
201
  <dim>-1</dim>
@@ -205,27 +713,111 @@
205
  </layer>
206
  </layers>
207
  <edges>
208
- <edge from-layer="0" from-port="0" to-layer="3" to-port="1" />
209
- <edge from-layer="1" from-port="0" to-layer="4" to-port="0" />
210
- <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
211
- <edge from-layer="3" from-port="4" to-layer="4" to-port="1" />
212
- <edge from-layer="3" from-port="3" to-layer="6" to-port="0" />
213
- <edge from-layer="3" from-port="2" to-layer="8" to-port="1" />
214
- <edge from-layer="3" from-port="3" to-layer="13" to-port="2" />
215
- <edge from-layer="3" from-port="2" to-layer="13" to-port="1" />
216
- <edge from-layer="3" from-port="4" to-layer="12" to-port="1" />
217
- <edge from-layer="4" from-port="2" to-layer="8" to-port="0" />
218
- <edge from-layer="5" from-port="0" to-layer="7" to-port="0" />
219
- <edge from-layer="6" from-port="1" to-layer="7" to-port="1" />
220
- <edge from-layer="7" from-port="2" to-layer="8" to-port="2" />
221
- <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
222
- <edge from-layer="9" from-port="1" to-layer="10" to-port="0" />
223
- <edge from-layer="11" from-port="0" to-layer="12" to-port="0" />
224
- <edge from-layer="12" from-port="2" to-layer="13" to-port="0" />
225
- <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
226
- <edge from-layer="14" from-port="1" to-layer="15" to-port="0" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
227
  </edges>
228
  <rt_info>
 
 
 
 
 
 
 
229
  <eos_token_id value="2" />
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
230
  </rt_info>
231
  </net>
 
1
  <?xml version="1.0"?>
2
  <net name="tokenizer" version="11">
3
  <layers>
4
+ <layer id="0" name="Parameter_70614" type="Parameter" version="opset1">
5
  <data shape="?" element_type="string" />
6
  <output>
7
+ <port id="0" precision="STRING" names="Parameter_70614">
8
  <dim>-1</dim>
9
  </port>
10
  </output>
11
  </layer>
12
+ <layer id="1" name="Constant_70735" 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_70736" 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_70737" 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_70620" 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_70615" 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_70616" 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_70617" 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_70618" 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_70619" 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_70621" 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_70622" 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_70623" 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_70624" 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_70625" 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_70626" 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_70627" 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_70691" type="Const" version="opset1">
155
+ <data element_type="u8" shape="23" offset="24" size="23" />
156
+ <output>
157
+ <port id="0" precision="U8">
158
+ <dim>23</dim>
159
+ </port>
160
+ </output>
161
+ </layer>
162
+ <layer id="18" name="SpecialTokensSplit_70692" 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>23</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_70694" type="Const" version="opset1">
205
+ <data element_type="u8" shape="13" offset="47" 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_70696" type="Const" version="opset1">
213
+ <data element_type="u8" shape="5" offset="60" 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_70697" 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_70699" type="Const" version="opset1">
258
+ <data element_type="u8" shape="1" offset="65" 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_70701" type="Const" version="opset1">
266
+ <data element_type="u8" shape="3" offset="66" 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_70702" 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_70704" type="Const" version="opset1">
311
+ <data element_type="i32" shape="32000" offset="69" size="128000" />
312
+ <output>
313
+ <port id="0" precision="I32">
314
+ <dim>32000</dim>
315
+ </port>
316
+ </output>
317
+ </layer>
318
+ <layer id="26" name="Constant_70706" type="Const" version="opset1">
319
+ <data element_type="i32" shape="32000" offset="128069" size="128000" />
320
+ <output>
321
+ <port id="0" precision="I32">
322
+ <dim>32000</dim>
323
+ </port>
324
+ </output>
325
+ </layer>
326
+ <layer id="27" name="Constant_70708" type="Const" version="opset1">
327
+ <data element_type="u8" shape="210919" offset="256069" size="210919" />
328
+ <output>
329
+ <port id="0" precision="U8">
330
+ <dim>210919</dim>
331
+ </port>
332
+ </output>
333
+ </layer>
334
+ <layer id="28" name="Constant_70716" type="Const" version="opset1">
335
+ <data element_type="i32" shape="61249" offset="466988" 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_70718" type="Const" version="opset1">
343
+ <data element_type="i32" shape="61249" offset="711984" 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_70720" type="Const" version="opset1">
351
+ <data element_type="u8" shape="254123" offset="956980" 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_70722" type="Const" version="opset1">
359
+ <data element_type="i32" shape="61249" offset="1211103" 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_70724" type="Const" version="opset1">
367
+ <data element_type="i32" shape="61249" offset="1456099" 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_70726" type="Const" version="opset1">
375
+ <data element_type="u8" shape="167806" offset="1701095" 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_70710" type="Const" version="opset1">
383
+ <data element_type="i32" shape="2" offset="1868901" size="8" />
384
+ <output>
385
+ <port id="0" precision="I32">
386
+ <dim>2</dim>
387
+ </port>
388
+ </output>
389
+ </layer>
390
+ <layer id="35" name="Constant_70712" type="Const" version="opset1">
391
+ <data element_type="i32" shape="2" offset="1868909" size="8" />
392
+ <output>
393
+ <port id="0" precision="I32">
394
+ <dim>2</dim>
395
+ </port>
396
+ </output>
397
+ </layer>
398
+ <layer id="36" name="Constant_70714" type="Const" version="opset1">
399
+ <data element_type="u8" shape="7" offset="1868917" size="7" />
400
+ <output>
401
+ <port id="0" precision="U8">
402
+ <dim>7</dim>
403
+ </port>
404
+ </output>
405
+ </layer>
406
+ <layer id="37" name="Constant_70727" type="Const" version="opset1">
407
+ <data element_type="i32" shape="2" offset="1868924" size="8" />
408
+ <output>
409
+ <port id="0" precision="I32">
410
+ <dim>2</dim>
411
+ </port>
412
+ </output>
413
+ </layer>
414
+ <layer id="38" name="BPETokenizer_70728" 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>32000</dim>
434
+ </port>
435
+ <port id="6" precision="I32">
436
+ <dim>32000</dim>
437
+ </port>
438
+ <port id="7" precision="U8">
439
+ <dim>210919</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>2</dim>
461
+ </port>
462
+ <port id="15" precision="I32">
463
+ <dim>2</dim>
464
+ </port>
465
+ <port id="16" precision="U8">
466
+ <dim>7</dim>
467
+ </port>
468
+ <port id="17" precision="I32">
469
+ <dim>2</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="Constant_70729" type="Const" version="opset1">
485
+ <data element_type="i32" shape="" offset="1868932" size="4" />
486
+ <output>
487
+ <port id="0" precision="I32" />
488
+ </output>
489
+ </layer>
490
+ <layer id="40" name="Constant_70731" type="Const" version="opset1">
491
+ <data element_type="u8" shape="4" offset="1868936" size="4" />
492
+ <output>
493
+ <port id="0" precision="U8">
494
+ <dim>4</dim>
495
+ </port>
496
+ </output>
497
+ </layer>
498
+ <layer id="41" name="Constant_70733" type="Const" version="opset1">
499
+ <data element_type="u8" shape="13" offset="1868940" size="13" />
500
+ <output>
501
+ <port id="0" precision="U8">
502
+ <dim>13</dim>
503
+ </port>
504
+ </output>
505
+ </layer>
506
+ <layer id="42" name="Truncate_70734" type="Truncate" version="extension">
507
+ <data m_num_inputs="1" />
508
  <input>
509
  <port id="0" precision="I32">
510
  <dim>-1</dim>
511
+ </port>
512
+ <port id="1" precision="I32">
513
  <dim>-1</dim>
514
  </port>
515
+ <port id="2" precision="I32">
516
+ <dim>-1</dim>
517
+ </port>
518
+ <port id="3" precision="I32" />
519
+ <port id="4" precision="U8">
520
+ <dim>4</dim>
521
+ </port>
522
+ <port id="5" precision="U8">
523
+ <dim>13</dim>
524
+ </port>
525
  </input>
526
  <output>
527
+ <port id="6" precision="I32">
528
+ <dim>-1</dim>
529
+ </port>
530
+ <port id="7" precision="I32">
531
  <dim>-1</dim>
532
+ </port>
533
+ <port id="8" precision="I32">
534
  <dim>-1</dim>
535
  </port>
536
  </output>
537
  </layer>
538
+ <layer id="43" name="Constant_70738" type="Const" version="opset1">
539
+ <data element_type="i32" shape="2" offset="8" size="8" />
540
  <output>
541
+ <port id="0" precision="I32">
542
+ <dim>2</dim>
543
+ </port>
544
  </output>
545
  </layer>
546
+ <layer id="44" name="CombineSegments_70739" type="CombineSegments" version="extension">
 
547
  <input>
548
  <port id="0" precision="I32" />
549
+ <port id="1" precision="I32" />
550
+ <port id="2" precision="I32">
551
+ <dim>1</dim>
552
+ </port>
553
+ <port id="3" precision="I32">
554
+ <dim>-1</dim>
555
+ </port>
556
+ <port id="4" precision="I32">
557
+ <dim>-1</dim>
558
+ </port>
559
+ <port id="5" precision="I32">
560
+ <dim>-1</dim>
561
+ </port>
562
+ <port id="6" precision="I32">
563
  <dim>2</dim>
564
  </port>
565
  </input>
566
  <output>
567
+ <port id="7" precision="I32">
568
  <dim>-1</dim>
569
+ </port>
570
+ <port id="8" precision="I32">
571
+ <dim>-1</dim>
572
+ </port>
573
+ <port id="9" precision="I32">
574
+ <dim>-1</dim>
575
+ </port>
576
+ <port id="10" precision="I32">
577
+ <dim>-1</dim>
578
+ </port>
579
+ <port id="11" precision="I32">
580
+ <dim>-1</dim>
581
+ </port>
582
+ <port id="12" precision="I32">
583
  <dim>-1</dim>
584
  </port>
585
  </output>
586
  </layer>
587
+ <layer id="45" name="Subtract_70740" type="Subtract" version="opset1">
588
+ <data auto_broadcast="numpy" />
589
  <input>
590
  <port id="0" precision="I32">
591
  <dim>-1</dim>
592
+ </port>
593
+ <port id="1" precision="I32">
594
  <dim>-1</dim>
595
  </port>
596
+ </input>
597
+ <output>
598
+ <port id="2" precision="I32">
599
+ <dim>-1</dim>
600
+ </port>
601
+ </output>
602
+ </layer>
603
+ <layer id="46" name="Constant_70741" type="Const" version="opset1">
604
+ <data element_type="i32" shape="" offset="0" size="4" />
605
+ <output>
606
+ <port id="0" precision="I32" />
607
+ </output>
608
+ </layer>
609
+ <layer id="47" name="ReduceMax_70742" type="ReduceMax" version="opset1">
610
+ <data keep_dims="false" />
611
+ <input>
612
+ <port id="0" precision="I32">
613
+ <dim>-1</dim>
614
+ </port>
615
+ <port id="1" precision="I32" />
616
+ </input>
617
+ <output>
618
+ <port id="2" precision="I32" />
619
+ </output>
620
+ </layer>
621
+ <layer id="48" name="Constant_70743" type="Const" version="opset1">
622
+ <data element_type="i32" shape="" offset="1868953" size="4" />
623
+ <output>
624
+ <port id="0" precision="I32" />
625
+ </output>
626
+ </layer>
627
+ <layer id="49" name="RaggedToDense_70744" type="RaggedToDense" version="extension">
628
+ <data pad_right="false" m_pad_max_length="false" />
629
+ <input>
630
+ <port id="0" precision="I32">
631
+ <dim>-1</dim>
632
+ </port>
633
+ <port id="1" precision="I32">
634
  <dim>-1</dim>
 
635
  </port>
636
  <port id="2" precision="I32">
637
  <dim>-1</dim>
638
  </port>
639
+ <port id="3" precision="I32" />
640
+ <port id="4" precision="I32" />
641
  </input>
642
  <output>
643
+ <port id="5" precision="I32">
644
+ <dim>-1</dim>
645
+ <dim>-1</dim>
646
+ </port>
647
+ <port id="6" precision="BOOL">
648
+ <dim>-1</dim>
649
+ <dim>-1</dim>
650
+ </port>
651
+ </output>
652
+ </layer>
653
+ <layer id="50" name="Convert_70745" type="Convert" version="opset1">
654
+ <data destination_type="i32" />
655
+ <input>
656
+ <port id="0" precision="BOOL">
657
+ <dim>-1</dim>
658
+ <dim>-1</dim>
659
+ </port>
660
+ </input>
661
+ <output>
662
+ <port id="1" precision="I32">
663
+ <dim>-1</dim>
664
+ <dim>-1</dim>
665
+ </port>
666
+ </output>
667
+ </layer>
668
+ <layer id="51" name="Convert_70745.0" type="Convert" version="opset1">
669
+ <data destination_type="i64" />
670
+ <input>
671
+ <port id="0" precision="I32">
672
+ <dim>-1</dim>
673
+ <dim>-1</dim>
674
+ </port>
675
+ </input>
676
+ <output>
677
+ <port id="1" precision="I64" names="attention_mask">
678
  <dim>-1</dim>
679
  <dim>-1</dim>
680
  </port>
681
  </output>
682
  </layer>
683
+ <layer id="53" name="RaggedToDense_70744.0" type="Convert" version="opset1">
684
  <data destination_type="i64" />
685
  <input>
686
  <port id="0" precision="I32">
 
695
  </port>
696
  </output>
697
  </layer>
698
+ <layer id="54" name="Result_70748" type="Result" version="opset1" output_names="input_ids">
699
  <input>
700
  <port id="0" precision="I64">
701
  <dim>-1</dim>
 
703
  </port>
704
  </input>
705
  </layer>
706
+ <layer id="52" name="Result_70750" type="Result" version="opset1" output_names="attention_mask">
707
  <input>
708
  <port id="0" precision="I64">
709
  <dim>-1</dim>
 
713
  </layer>
714
  </layers>
715
  <edges>
716
+ <edge from-layer="0" from-port="0" to-layer="5" to-port="0" />
717
+ <edge from-layer="1" from-port="0" to-layer="44" to-port="0" />
718
+ <edge from-layer="2" from-port="0" to-layer="44" to-port="1" />
719
+ <edge from-layer="3" from-port="0" to-layer="44" to-port="2" />
720
+ <edge from-layer="4" from-port="0" to-layer="11" to-port="0" />
721
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="0" />
722
+ <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
723
+ <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
724
+ <edge from-layer="5" from-port="1" to-layer="18" to-port="2" />
725
+ <edge from-layer="6" from-port="1" to-layer="9" to-port="0" />
726
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="1" />
727
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="2" />
728
+ <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
729
+ <edge from-layer="9" from-port="3" to-layer="11" to-port="1" />
730
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="2" />
731
+ <edge from-layer="11" from-port="3" to-layer="18" to-port="0" />
732
+ <edge from-layer="12" from-port="0" to-layer="16" to-port="0" />
733
+ <edge from-layer="13" from-port="0" to-layer="14" to-port="1" />
734
+ <edge from-layer="14" from-port="2" to-layer="16" to-port="1" />
735
+ <edge from-layer="15" from-port="0" to-layer="16" to-port="2" />
736
+ <edge from-layer="16" from-port="3" to-layer="18" to-port="1" />
737
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="5" />
738
+ <edge from-layer="18" from-port="6" to-layer="38" to-port="0" />
739
+ <edge from-layer="18" from-port="7" to-layer="38" to-port="1" />
740
+ <edge from-layer="18" from-port="11" to-layer="21" to-port="3" />
741
+ <edge from-layer="18" from-port="10" to-layer="21" to-port="2" />
742
+ <edge from-layer="18" from-port="9" to-layer="21" to-port="1" />
743
+ <edge from-layer="18" from-port="8" to-layer="21" to-port="0" />
744
+ <edge from-layer="19" from-port="0" to-layer="21" to-port="4" />
745
+ <edge from-layer="20" from-port="0" to-layer="21" to-port="5" />
746
+ <edge from-layer="21" from-port="6" to-layer="24" to-port="0" />
747
+ <edge from-layer="21" from-port="9" to-layer="24" to-port="3" />
748
+ <edge from-layer="21" from-port="8" to-layer="24" to-port="2" />
749
+ <edge from-layer="21" from-port="7" to-layer="24" to-port="1" />
750
+ <edge from-layer="22" from-port="0" to-layer="24" to-port="4" />
751
+ <edge from-layer="23" from-port="0" to-layer="24" to-port="5" />
752
+ <edge from-layer="24" from-port="6" to-layer="38" to-port="2" />
753
+ <edge from-layer="24" from-port="7" to-layer="38" to-port="3" />
754
+ <edge from-layer="24" from-port="8" to-layer="38" to-port="4" />
755
+ <edge from-layer="25" from-port="0" to-layer="38" to-port="5" />
756
+ <edge from-layer="26" from-port="0" to-layer="38" to-port="6" />
757
+ <edge from-layer="27" from-port="0" to-layer="38" to-port="7" />
758
+ <edge from-layer="28" from-port="0" to-layer="38" to-port="8" />
759
+ <edge from-layer="29" from-port="0" to-layer="38" to-port="9" />
760
+ <edge from-layer="30" from-port="0" to-layer="38" to-port="10" />
761
+ <edge from-layer="31" from-port="0" to-layer="38" to-port="11" />
762
+ <edge from-layer="32" from-port="0" to-layer="38" to-port="12" />
763
+ <edge from-layer="33" from-port="0" to-layer="38" to-port="13" />
764
+ <edge from-layer="34" from-port="0" to-layer="38" to-port="14" />
765
+ <edge from-layer="35" from-port="0" to-layer="38" to-port="15" />
766
+ <edge from-layer="36" from-port="0" to-layer="38" to-port="16" />
767
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="17" />
768
+ <edge from-layer="38" from-port="18" to-layer="42" to-port="0" />
769
+ <edge from-layer="38" from-port="19" to-layer="42" to-port="1" />
770
+ <edge from-layer="38" from-port="20" to-layer="42" to-port="2" />
771
+ <edge from-layer="39" from-port="0" to-layer="42" to-port="3" />
772
+ <edge from-layer="40" from-port="0" to-layer="42" to-port="4" />
773
+ <edge from-layer="41" from-port="0" to-layer="42" to-port="5" />
774
+ <edge from-layer="42" from-port="8" to-layer="44" to-port="5" />
775
+ <edge from-layer="42" from-port="7" to-layer="44" to-port="4" />
776
+ <edge from-layer="42" from-port="6" to-layer="44" to-port="3" />
777
+ <edge from-layer="43" from-port="0" to-layer="44" to-port="6" />
778
+ <edge from-layer="44" from-port="8" to-layer="45" to-port="0" />
779
+ <edge from-layer="44" from-port="7" to-layer="45" to-port="1" />
780
+ <edge from-layer="44" from-port="7" to-layer="49" to-port="0" />
781
+ <edge from-layer="44" from-port="8" to-layer="49" to-port="1" />
782
+ <edge from-layer="44" from-port="9" to-layer="49" to-port="2" />
783
+ <edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
784
+ <edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
785
+ <edge from-layer="47" from-port="2" to-layer="49" to-port="3" />
786
+ <edge from-layer="48" from-port="0" to-layer="49" to-port="4" />
787
+ <edge from-layer="49" from-port="6" to-layer="50" to-port="0" />
788
+ <edge from-layer="49" from-port="5" to-layer="53" to-port="0" />
789
+ <edge from-layer="50" from-port="1" to-layer="51" to-port="0" />
790
+ <edge from-layer="51" from-port="1" to-layer="52" to-port="0" />
791
+ <edge from-layer="53" from-port="1" to-layer="54" to-port="0" />
792
  </edges>
793
  <rt_info>
794
+ <add_attention_mask value="True" />
795
+ <add_prefix_space />
796
+ <add_special_tokens value="True" />
797
+ <bos_token_id value="1" />
798
+ <chat_template value="{% for message in messages %}&#10;{% if message['role'] == 'user' %}&#10;{{ '&lt;|user|>&#10;' + message['content'] + eos_token }}&#10;{% elif message['role'] == 'system' %}&#10;{{ '&lt;|system|>&#10;' + message['content'] + eos_token }}&#10;{% elif message['role'] == 'assistant' %}&#10;{{ '&lt;|assistant|>&#10;' + message['content'] + eos_token }}&#10;{% endif %}&#10;{% if loop.last and add_generation_prompt %}&#10;{{ '&lt;|assistant|>' }}&#10;{% endif %}&#10;{% endfor %}" />
799
+ <clean_up_tokenization_spaces />
800
+ <detokenizer_input_type value="i64" />
801
  <eos_token_id value="2" />
802
+ <handle_special_tokens_with_re />
803
+ <max_length />
804
+ <number_of_inputs value="1" />
805
+ <openvino_tokenizers_version value="2025.4.0.0-625-3694f87878e" />
806
+ <openvino_version value="2025.4.0-20398-7a975177ff4-releases/2025/4" />
807
+ <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;pair&quot;: [{&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 0}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;A&quot;, &quot;type_id&quot;: 0}}, {&quot;SpecialToken&quot;: {&quot;id&quot;: &quot;&lt;s>&quot;, &quot;type_id&quot;: 1}}, {&quot;Sequence&quot;: {&quot;id&quot;: &quot;B&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;]}}}" />
808
+ <original_tokenizer_class value="&lt;class 'transformers.models.llama.tokenization_llama_fast.LlamaTokenizerFast'>" />
809
+ <pad_token_id value="2" />
810
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [1, -1], &quot;type_ids&quot;: [0, 0]}, &quot;pair&quot;: {&quot;ids&quot;: [1, -1, 1, -2], &quot;type_ids&quot;: [0, 0, 1, 1]}}" />
811
+ <sentencepiece_version value="0.2.1" />
812
+ <skip_special_tokens value="True" />
813
+ <streaming_detokenizer value="False" />
814
+ <tiktoken_version value="0.12.0" />
815
+ <tokenizer_output_type value="i64" />
816
+ <tokenizers_version value="0.21.4" />
817
+ <transformers_version value="4.55.4" />
818
+ <use_max_padding value="False" />
819
+ <use_sentencepiece_backend value="False" />
820
+ <utf8_replace_mode value="replace" />
821
+ <with_detokenizer value="True" />
822
  </rt_info>
823
  </net>
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
@@ -28,9 +29,9 @@
28
  }
29
  },
30
  "bos_token": "<s>",
31
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
 
34
  "legacy": false,
35
  "model_max_length": 2048,
36
  "pad_token": "</s>",
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
 
29
  }
30
  },
31
  "bos_token": "<s>",
 
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
  "legacy": false,
36
  "model_max_length": 2048,
37
  "pad_token": "</s>",