Hugging Face's logo

llmware
/
phi-3.5-vision-ov

OpenVINO
phi3_v
green
llmware-vision
p3
ov
emerald
custom_code
Model card Files
xet
Community
doberst commited on
Commit
d7246c0
·
verified ·
1 Parent(s): 17c0d7a

Upload 20 files

Browse files
Files changed (20) hide show
  1. chat_template.json +3 -0
  2. config.json +0 -0
  3. generation_config.json +7 -0
  4. openvino_config.json +43 -0
  5. openvino_detokenizer.bin +3 -0
  6. openvino_detokenizer.xml +351 -0
  7. openvino_language_model.bin +3 -0
  8. openvino_language_model.xml +0 -0
  9. openvino_text_embeddings_model.bin +3 -0
  10. openvino_text_embeddings_model.xml +176 -0
  11. openvino_tokenizer.bin +3 -0
  12. openvino_tokenizer.xml +821 -0
  13. openvino_vision_embeddings_model.bin +3 -0
  14. openvino_vision_embeddings_model.xml +0 -0
  15. openvino_vision_projection_model.bin +3 -0
  16. openvino_vision_projection_model.xml +334 -0
  17. preprocessor_config.json +21 -0
  18. special_tokens_map.json +36 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +414 -0
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}"
3
+ }
config.json ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.51.0"
7
+ }
openvino_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dtype": "int4",
3
+ "input_info": null,
4
+ "optimum_version": "2.1.0.dev0",
5
+ "quantization_config": {
6
+ "_dataset_kwargs": {},
7
+ "dataset": null,
8
+ "default_config": {
9
+ "quant_method": "default"
10
+ },
11
+ "ignored_scope": null,
12
+ "num_samples": null,
13
+ "processor": "microsoft/Phi-3.5-vision-instruct",
14
+ "quantization_configs": {
15
+ "lm_model": {
16
+ "_dataset_kwargs": {},
17
+ "all_layers": null,
18
+ "backup_precision": null,
19
+ "bits": 4,
20
+ "dataset": null,
21
+ "dq_group_size": null,
22
+ "dtype": "int4",
23
+ "gptq": null,
24
+ "group_size": 128,
25
+ "group_size_fallback": null,
26
+ "ignored_scope": null,
27
+ "lora_correction": null,
28
+ "num_samples": null,
29
+ "processor": "microsoft/Phi-3.5-vision-instruct",
30
+ "quant_method": "default",
31
+ "ratio": 1.0,
32
+ "scale_estimation": null,
33
+ "sensitivity_metric": null,
34
+ "statistics_path": null,
35
+ "sym": false,
36
+ "tokenizer": "microsoft/Phi-3.5-vision-instruct"
37
+ }
38
+ },
39
+ "tokenizer": "microsoft/Phi-3.5-vision-instruct"
40
+ },
41
+ "save_onnx_model": false,
42
+ "transformers_version": "4.51.0"
43
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e78c9faefd49e7270e61a5513321675a0cd7f98513fbc60654702a90983182b
3
+ size 468188
openvino_detokenizer.xml ADDED
@@ -0,0 +1,351 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_138" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_138">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_342" 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_91" type="Const" version="opset1">
29
+ <data element_type="i32" shape="32045" offset="0" size="128180" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>32045</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_93" type="Const" version="opset1">
37
+ <data element_type="i32" shape="32045" offset="128180" size="128180" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>32045</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_95" type="Const" version="opset1">
45
+ <data element_type="u8" shape="211633" offset="256360" size="211633" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>211633</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_143" type="Const" version="opset1">
53
+ <data element_type="i32" shape="47" offset="467993" size="188" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>47</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_145" 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>32045</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>32045</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>211633</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>47</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_147" type="Const" version="opset1">
99
+ <data element_type="u8" shape="3" offset="468181" 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_149" type="Const" version="opset1">
107
+ <data element_type="u8" shape="1" offset="468184" 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_150" 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_151" 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_152" 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_154" type="Const" version="opset1">
194
+ <data element_type="u8" shape="2" offset="468185" 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_156" type="Const" version="opset1">
202
+ <data element_type="u8" shape="0" offset="468187" 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_157" 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_158" 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_159" 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_160,string_output">
279
+ <dim>-1</dim>
280
+ </port>
281
+ </output>
282
+ </layer>
283
+ <layer id="17" name="Result_160" type="Result" version="opset1" output_names="Result_160,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 %}{{'&lt;|' + message['role'] + '|>' + '&#10;' + message['content'] + '&lt;|end|>&#10;' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '&lt;|assistant|>&#10;' -}}{% 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="2025.4.1.0-627-e79796a77f3" />
336
+ <openvino_version value="2025.4.1-20426-82bbf0292c5-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="32000" />
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
+ <skip_special_tokens value="True" />
342
+ <streaming_detokenizer value="False" />
343
+ <tokenizer_output_type value="i64" />
344
+ <tokenizers_version value="0.22.2" />
345
+ <transformers_version value="4.57.3" />
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_language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2255794038d33306bc1540e13904082dd77facd9e33999c102abed034f9c5a4
3
+ size 1982114226
openvino_language_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_text_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8295cb8c1b0a2ab714d0d309b47015967e11c2b5205e038abff0d6f229b3bc
3
+ size 98564740
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model9" version="11">
3
+ <layers>
4
+ <layer id="0" name="input" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="input">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="self.weight" type="Const" version="opset1">
14
+ <data element_type="i8" shape="32064, 3072" offset="0" size="98500608" />
15
+ <output>
16
+ <port id="0" precision="I8">
17
+ <dim>32064</dim>
18
+ <dim>3072</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="Convert_829947" type="Convert" version="opset1">
23
+ <data destination_type="f16" />
24
+ <input>
25
+ <port id="0" precision="I8">
26
+ <dim>32064</dim>
27
+ <dim>3072</dim>
28
+ </port>
29
+ </input>
30
+ <output>
31
+ <port id="1" precision="FP16">
32
+ <dim>32064</dim>
33
+ <dim>3072</dim>
34
+ </port>
35
+ </output>
36
+ </layer>
37
+ <layer id="3" name="self.weight/scale" type="Const" version="opset1">
38
+ <data element_type="f16" shape="32064, 1" offset="98500608" size="64128" />
39
+ <output>
40
+ <port id="0" precision="FP16">
41
+ <dim>32064</dim>
42
+ <dim>1</dim>
43
+ </port>
44
+ </output>
45
+ </layer>
46
+ <layer id="4" name="self.weight/fq_weights_0" type="Multiply" version="opset1">
47
+ <data auto_broadcast="numpy" />
48
+ <input>
49
+ <port id="0" precision="FP16">
50
+ <dim>32064</dim>
51
+ <dim>3072</dim>
52
+ </port>
53
+ <port id="1" precision="FP16">
54
+ <dim>32064</dim>
55
+ <dim>1</dim>
56
+ </port>
57
+ </input>
58
+ <output>
59
+ <port id="2" precision="FP16">
60
+ <dim>32064</dim>
61
+ <dim>3072</dim>
62
+ </port>
63
+ </output>
64
+ </layer>
65
+ <layer id="5" name="self.weight/fq_weights_0/convert" type="Convert" version="opset1">
66
+ <data destination_type="f32" />
67
+ <input>
68
+ <port id="0" precision="FP16">
69
+ <dim>32064</dim>
70
+ <dim>3072</dim>
71
+ </port>
72
+ </input>
73
+ <output>
74
+ <port id="1" precision="FP32">
75
+ <dim>32064</dim>
76
+ <dim>3072</dim>
77
+ </port>
78
+ </output>
79
+ </layer>
80
+ <layer id="6" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
81
+ <data destination_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64">
84
+ <dim>-1</dim>
85
+ <dim>-1</dim>
86
+ </port>
87
+ </input>
88
+ <output>
89
+ <port id="1" precision="I32">
90
+ <dim>-1</dim>
91
+ <dim>-1</dim>
92
+ </port>
93
+ </output>
94
+ </layer>
95
+ <layer id="7" name="ov_ext::embedding/Constant" type="Const" version="opset1">
96
+ <data element_type="i32" shape="" offset="98564736" size="4" />
97
+ <output>
98
+ <port id="0" precision="I32" />
99
+ </output>
100
+ </layer>
101
+ <layer id="8" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
102
+ <data batch_dims="0" />
103
+ <input>
104
+ <port id="0" precision="FP32">
105
+ <dim>32064</dim>
106
+ <dim>3072</dim>
107
+ </port>
108
+ <port id="1" precision="I32">
109
+ <dim>-1</dim>
110
+ <dim>-1</dim>
111
+ </port>
112
+ <port id="2" precision="I32" />
113
+ </input>
114
+ <output>
115
+ <port id="3" precision="FP32" names="inputs_embeds">
116
+ <dim>-1</dim>
117
+ <dim>-1</dim>
118
+ <dim>3072</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="9" name="Result_186155" type="Result" version="opset1" output_names="inputs_embeds">
123
+ <input>
124
+ <port id="0" precision="FP32">
125
+ <dim>-1</dim>
126
+ <dim>-1</dim>
127
+ <dim>3072</dim>
128
+ </port>
129
+ </input>
130
+ </layer>
131
+ </layers>
132
+ <edges>
133
+ <edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
134
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
135
+ <edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
136
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
137
+ <edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
138
+ <edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
139
+ <edge from-layer="6" from-port="1" to-layer="8" to-port="1" />
140
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
141
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
142
+ </edges>
143
+ <rt_info>
144
+ <Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
145
+ <conversion_parameters>
146
+ <framework value="pytorch" />
147
+ <is_python_object value="True" />
148
+ </conversion_parameters>
149
+ <nncf>
150
+ <friendly_names_were_updated value="True" />
151
+ <version value="2.19.0" />
152
+ <weight_compression>
153
+ <advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
154
+ <all_layers value="False" />
155
+ <awq value="False" />
156
+ <backup_mode value="int8_asym" />
157
+ <compression_format value="dequantize" />
158
+ <gptq value="False" />
159
+ <group_size value="-1" />
160
+ <ignored_scope value="[]" />
161
+ <lora_correction value="False" />
162
+ <mode value="int8_sym" />
163
+ <ratio value="1.0" />
164
+ <scale_estimation value="False" />
165
+ <sensitivity_metric value="weight_quantization_error" />
166
+ </weight_compression>
167
+ </nncf>
168
+ <optimum>
169
+ <nncf_version value="2.19.0" />
170
+ <optimum_intel_version value="1.27.0.dev0+132f70d" />
171
+ <optimum_version value="2.1.0.dev0" />
172
+ <pytorch_version value="2.9.1+cpu" />
173
+ <transformers_version value="4.51.0" />
174
+ </optimum>
175
+ </rt_info>
176
+ </net>
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bdc79863cc6e1920cb50f01fc3122748d50205c058805abbeb747e3827a561
3
+ size 1872234
openvino_tokenizer.xml ADDED
@@ -0,0 +1,821 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_1" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_1">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_122" 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_123" 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_124" 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_7" type="Const" version="opset1">
33
+ <data element_type="i32" shape="" offset="0" size="4" />
34
+ <output>
35
+ <port id="0" precision="I32" />
36
+ </output>
37
+ </layer>
38
+ <layer id="5" name="StringTensorUnpack_2" 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_3" 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_4" type="Const" version="opset1">
70
+ <data element_type="i32" shape="" offset="0" size="4" />
71
+ <output>
72
+ <port id="0" precision="I32" />
73
+ </output>
74
+ </layer>
75
+ <layer id="8" name="Constant_5" type="Const" version="opset1">
76
+ <data element_type="i32" shape="" offset="0" size="4" />
77
+ <output>
78
+ <port id="0" precision="I32" />
79
+ </output>
80
+ </layer>
81
+ <layer id="9" name="Gather_6" 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="I32" />
88
+ <port id="2" precision="I32" />
89
+ </input>
90
+ <output>
91
+ <port id="3" precision="I64" />
92
+ </output>
93
+ </layer>
94
+ <layer id="10" name="Constant_8" type="Const" version="opset1">
95
+ <data element_type="i32" shape="" offset="4" size="4" />
96
+ <output>
97
+ <port id="0" precision="I32" />
98
+ </output>
99
+ </layer>
100
+ <layer id="11" name="Range_9" type="Range" version="opset4">
101
+ <data output_type="i32" />
102
+ <input>
103
+ <port id="0" precision="I32" />
104
+ <port id="1" precision="I64" />
105
+ <port id="2" precision="I32" />
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_10" type="Const" version="opset1">
114
+ <data element_type="i32" shape="" offset="4" size="4" />
115
+ <output>
116
+ <port id="0" precision="I32" />
117
+ </output>
118
+ </layer>
119
+ <layer id="13" name="Constant_11" type="Const" version="opset1">
120
+ <data element_type="i64" shape="" offset="8" size="8" />
121
+ <output>
122
+ <port id="0" precision="I64" />
123
+ </output>
124
+ </layer>
125
+ <layer id="14" name="Add_12" 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_13" type="Const" version="opset1">
136
+ <data element_type="i32" shape="" offset="4" size="4" />
137
+ <output>
138
+ <port id="0" precision="I32" />
139
+ </output>
140
+ </layer>
141
+ <layer id="16" name="Range_14" type="Range" version="opset4">
142
+ <data output_type="i32" />
143
+ <input>
144
+ <port id="0" precision="I32" />
145
+ <port id="1" precision="I64" />
146
+ <port id="2" precision="I32" />
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_78" type="Const" version="opset1">
155
+ <data element_type="u8" shape="971" offset="16" size="971" />
156
+ <output>
157
+ <port id="0" precision="U8">
158
+ <dim>971</dim>
159
+ </port>
160
+ </output>
161
+ </layer>
162
+ <layer id="18" name="SpecialTokensSplit_79" 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>971</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_81" type="Const" version="opset1">
205
+ <data element_type="u8" shape="13" offset="987" 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_83" type="Const" version="opset1">
213
+ <data element_type="u8" shape="5" offset="1000" 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_84" 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_86" type="Const" version="opset1">
258
+ <data element_type="u8" shape="1" offset="1005" 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_88" type="Const" version="opset1">
266
+ <data element_type="u8" shape="3" offset="1006" 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_89" 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_91" type="Const" version="opset1">
311
+ <data element_type="i32" shape="32045" offset="1009" size="128180" />
312
+ <output>
313
+ <port id="0" precision="I32">
314
+ <dim>32045</dim>
315
+ </port>
316
+ </output>
317
+ </layer>
318
+ <layer id="26" name="Constant_93" type="Const" version="opset1">
319
+ <data element_type="i32" shape="32045" offset="129189" size="128180" />
320
+ <output>
321
+ <port id="0" precision="I32">
322
+ <dim>32045</dim>
323
+ </port>
324
+ </output>
325
+ </layer>
326
+ <layer id="27" name="Constant_95" type="Const" version="opset1">
327
+ <data element_type="u8" shape="211633" offset="257369" size="211633" />
328
+ <output>
329
+ <port id="0" precision="U8">
330
+ <dim>211633</dim>
331
+ </port>
332
+ </output>
333
+ </layer>
334
+ <layer id="28" name="Constant_103" type="Const" version="opset1">
335
+ <data element_type="i32" shape="61249" offset="469002" 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_105" type="Const" version="opset1">
343
+ <data element_type="i32" shape="61249" offset="713998" 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_107" type="Const" version="opset1">
351
+ <data element_type="u8" shape="254123" offset="958994" 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_109" type="Const" version="opset1">
359
+ <data element_type="i32" shape="61249" offset="1213117" 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_111" type="Const" version="opset1">
367
+ <data element_type="i32" shape="61249" offset="1458113" 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_113" type="Const" version="opset1">
375
+ <data element_type="u8" shape="167806" offset="1703109" 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_97" type="Const" version="opset1">
383
+ <data element_type="i32" shape="47" offset="1870915" size="188" />
384
+ <output>
385
+ <port id="0" precision="I32">
386
+ <dim>47</dim>
387
+ </port>
388
+ </output>
389
+ </layer>
390
+ <layer id="35" name="Constant_99" type="Const" version="opset1">
391
+ <data element_type="i32" shape="47" offset="1871103" size="188" />
392
+ <output>
393
+ <port id="0" precision="I32">
394
+ <dim>47</dim>
395
+ </port>
396
+ </output>
397
+ </layer>
398
+ <layer id="36" name="Constant_101" type="Const" version="opset1">
399
+ <data element_type="u8" shape="721" offset="1871291" size="721" />
400
+ <output>
401
+ <port id="0" precision="U8">
402
+ <dim>721</dim>
403
+ </port>
404
+ </output>
405
+ </layer>
406
+ <layer id="37" name="Constant_114" type="Const" version="opset1">
407
+ <data element_type="i32" shape="47" offset="1872012" size="188" />
408
+ <output>
409
+ <port id="0" precision="I32">
410
+ <dim>47</dim>
411
+ </port>
412
+ </output>
413
+ </layer>
414
+ <layer id="38" name="BPETokenizer_115" 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>32045</dim>
434
+ </port>
435
+ <port id="6" precision="I32">
436
+ <dim>32045</dim>
437
+ </port>
438
+ <port id="7" precision="U8">
439
+ <dim>211633</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>47</dim>
461
+ </port>
462
+ <port id="15" precision="I32">
463
+ <dim>47</dim>
464
+ </port>
465
+ <port id="16" precision="U8">
466
+ <dim>721</dim>
467
+ </port>
468
+ <port id="17" precision="I32">
469
+ <dim>47</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_116" type="Const" version="opset1">
485
+ <data element_type="i32" shape="" offset="1872200" size="4" />
486
+ <output>
487
+ <port id="0" precision="I32" />
488
+ </output>
489
+ </layer>
490
+ <layer id="40" name="Constant_118" type="Const" version="opset1">
491
+ <data element_type="u8" shape="5" offset="1872204" size="5" />
492
+ <output>
493
+ <port id="0" precision="U8">
494
+ <dim>5</dim>
495
+ </port>
496
+ </output>
497
+ </layer>
498
+ <layer id="41" name="Constant_120" type="Const" version="opset1">
499
+ <data element_type="u8" shape="13" offset="1872209" 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_121" 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>5</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_125" type="Const" version="opset1">
539
+ <data element_type="i32" shape="2" offset="1872222" 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_126" 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_127" 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_128" 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_129" 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_130" type="Const" version="opset1">
622
+ <data element_type="i32" shape="" offset="1872230" size="4" />
623
+ <output>
624
+ <port id="0" precision="I32" />
625
+ </output>
626
+ </layer>
627
+ <layer id="49" name="RaggedToDense_131" type="RaggedToDense" version="extension">
628
+ <data pad_right="true" 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_132" 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_132.0" 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_131.0" type="Convert" version="opset1">
684
+ <data destination_type="i64" />
685
+ <input>
686
+ <port id="0" precision="I32">
687
+ <dim>-1</dim>
688
+ <dim>-1</dim>
689
+ </port>
690
+ </input>
691
+ <output>
692
+ <port id="1" precision="I64" names="input_ids">
693
+ <dim>-1</dim>
694
+ <dim>-1</dim>
695
+ </port>
696
+ </output>
697
+ </layer>
698
+ <layer id="54" name="Result_135" type="Result" version="opset1" output_names="input_ids">
699
+ <input>
700
+ <port id="0" precision="I64">
701
+ <dim>-1</dim>
702
+ <dim>-1</dim>
703
+ </port>
704
+ </input>
705
+ </layer>
706
+ <layer id="52" name="Result_137" type="Result" version="opset1" output_names="attention_mask">
707
+ <input>
708
+ <port id="0" precision="I64">
709
+ <dim>-1</dim>
710
+ <dim>-1</dim>
711
+ </port>
712
+ </input>
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="1" to-layer="18" to-port="2" />
723
+ <edge from-layer="5" from-port="2" to-layer="18" to-port="3" />
724
+ <edge from-layer="5" from-port="3" to-layer="18" to-port="4" />
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="11" to-port="1" />
729
+ <edge from-layer="9" from-port="3" to-layer="14" to-port="0" />
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="11" to-layer="21" to-port="3" />
739
+ <edge from-layer="18" from-port="6" to-layer="38" to-port="0" />
740
+ <edge from-layer="18" from-port="7" to-layer="38" to-port="1" />
741
+ <edge from-layer="18" from-port="8" to-layer="21" to-port="0" />
742
+ <edge from-layer="18" from-port="10" to-layer="21" to-port="2" />
743
+ <edge from-layer="18" from-port="9" to-layer="21" to-port="1" />
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="9" to-layer="24" to-port="3" />
747
+ <edge from-layer="21" from-port="6" to-layer="24" to-port="0" />
748
+ <edge from-layer="21" from-port="7" to-layer="24" to-port="1" />
749
+ <edge from-layer="21" from-port="8" to-layer="24" to-port="2" />
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="6" to-layer="44" to-port="3" />
775
+ <edge from-layer="42" from-port="7" to-layer="44" to-port="4" />
776
+ <edge from-layer="42" from-port="8" to-layer="44" to-port="5" />
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 %}{{'&lt;|' + message['role'] + '|>' + '&#10;' + message['content'] + '&lt;|end|>&#10;' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '&lt;|assistant|>&#10;' -}}{% endif %}" />
799
+ <clean_up_tokenization_spaces />
800
+ <detokenizer_input_type value="i64" />
801
+ <eos_token_id value="32000" />
802
+ <handle_special_tokens_with_re />
803
+ <max_length />
804
+ <number_of_inputs value="1" />
805
+ <openvino_tokenizers_version value="2025.4.1.0-627-e79796a77f3" />
806
+ <openvino_version value="2025.4.1-20426-82bbf0292c5-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="32000" />
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
+ <skip_special_tokens value="True" />
812
+ <streaming_detokenizer value="False" />
813
+ <tokenizer_output_type value="i64" />
814
+ <tokenizers_version value="0.22.2" />
815
+ <transformers_version value="4.57.3" />
816
+ <use_max_padding value="False" />
817
+ <use_sentencepiece_backend value="False" />
818
+ <utf8_replace_mode value="replace" />
819
+ <with_detokenizer value="True" />
820
+ </rt_info>
821
+ </net>
openvino_vision_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb63340ca7e80ba5789d291b7c1d01888e1a773dd4c77fc9d1507df7ef0ff3d9
3
+ size 294035604
openvino_vision_embeddings_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_vision_projection_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e6b5f4c4ce54dde0bdd193e7346ef5641c12fcf8370167f14f26ad85f8f60d
3
+ size 22056960
openvino_vision_projection_model.xml ADDED
@@ -0,0 +1,334 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model3" version="11">
3
+ <layers>
4
+ <layer id="0" name="input" type="Parameter" version="opset1">
5
+ <data shape="?,?,4096" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="input">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ <dim>4096</dim>
11
+ </port>
12
+ </output>
13
+ </layer>
14
+ <layer id="1" name="self.0.weight" type="Const" version="opset1">
15
+ <data element_type="i8" shape="3072, 4096" offset="0" size="12582912" />
16
+ <output>
17
+ <port id="0" precision="I8">
18
+ <dim>3072</dim>
19
+ <dim>4096</dim>
20
+ </port>
21
+ </output>
22
+ </layer>
23
+ <layer id="2" name="Convert_1495763" type="Convert" version="opset1">
24
+ <data destination_type="f16" />
25
+ <input>
26
+ <port id="0" precision="I8">
27
+ <dim>3072</dim>
28
+ <dim>4096</dim>
29
+ </port>
30
+ </input>
31
+ <output>
32
+ <port id="1" precision="FP16">
33
+ <dim>3072</dim>
34
+ <dim>4096</dim>
35
+ </port>
36
+ </output>
37
+ </layer>
38
+ <layer id="3" name="self.0.weight/scale" type="Const" version="opset1">
39
+ <data element_type="f16" shape="3072, 1" offset="12582912" size="6144" />
40
+ <output>
41
+ <port id="0" precision="FP16">
42
+ <dim>3072</dim>
43
+ <dim>1</dim>
44
+ </port>
45
+ </output>
46
+ </layer>
47
+ <layer id="4" name="self.0.weight/fq_weights_1" type="Multiply" version="opset1">
48
+ <data auto_broadcast="numpy" />
49
+ <input>
50
+ <port id="0" precision="FP16">
51
+ <dim>3072</dim>
52
+ <dim>4096</dim>
53
+ </port>
54
+ <port id="1" precision="FP16">
55
+ <dim>3072</dim>
56
+ <dim>1</dim>
57
+ </port>
58
+ </input>
59
+ <output>
60
+ <port id="2" precision="FP16">
61
+ <dim>3072</dim>
62
+ <dim>4096</dim>
63
+ </port>
64
+ </output>
65
+ </layer>
66
+ <layer id="5" name="self.0.weight/fq_weights_1/convert" type="Convert" version="opset1">
67
+ <data destination_type="f32" />
68
+ <input>
69
+ <port id="0" precision="FP16">
70
+ <dim>3072</dim>
71
+ <dim>4096</dim>
72
+ </port>
73
+ </input>
74
+ <output>
75
+ <port id="1" precision="FP32">
76
+ <dim>3072</dim>
77
+ <dim>4096</dim>
78
+ </port>
79
+ </output>
80
+ </layer>
81
+ <layer id="6" name="__module.0/ov_ext::linear/MatMul" type="MatMul" version="opset1">
82
+ <data transpose_a="false" transpose_b="true" />
83
+ <input>
84
+ <port id="0" precision="FP32">
85
+ <dim>-1</dim>
86
+ <dim>-1</dim>
87
+ <dim>4096</dim>
88
+ </port>
89
+ <port id="1" precision="FP32">
90
+ <dim>3072</dim>
91
+ <dim>4096</dim>
92
+ </port>
93
+ </input>
94
+ <output>
95
+ <port id="2" precision="FP32">
96
+ <dim>-1</dim>
97
+ <dim>-1</dim>
98
+ <dim>3072</dim>
99
+ </port>
100
+ </output>
101
+ </layer>
102
+ <layer id="7" name="Constant_167806" type="Const" version="opset1">
103
+ <data element_type="f32" shape="1, 1, 3072" offset="12589056" size="12288" />
104
+ <output>
105
+ <port id="0" precision="FP32">
106
+ <dim>1</dim>
107
+ <dim>1</dim>
108
+ <dim>3072</dim>
109
+ </port>
110
+ </output>
111
+ </layer>
112
+ <layer id="8" name="__module.0/ov_ext::linear/Add" type="Add" version="opset1">
113
+ <data auto_broadcast="numpy" />
114
+ <input>
115
+ <port id="0" precision="FP32">
116
+ <dim>-1</dim>
117
+ <dim>-1</dim>
118
+ <dim>3072</dim>
119
+ </port>
120
+ <port id="1" precision="FP32">
121
+ <dim>1</dim>
122
+ <dim>1</dim>
123
+ <dim>3072</dim>
124
+ </port>
125
+ </input>
126
+ <output>
127
+ <port id="2" precision="FP32" names="11,input_1">
128
+ <dim>-1</dim>
129
+ <dim>-1</dim>
130
+ <dim>3072</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="9" name="__module.1/aten::gelu/Gelu" type="Gelu" version="opset7">
135
+ <data approximation_mode="ERF" />
136
+ <input>
137
+ <port id="0" precision="FP32">
138
+ <dim>-1</dim>
139
+ <dim>-1</dim>
140
+ <dim>3072</dim>
141
+ </port>
142
+ </input>
143
+ <output>
144
+ <port id="1" precision="FP32" names="13">
145
+ <dim>-1</dim>
146
+ <dim>-1</dim>
147
+ <dim>3072</dim>
148
+ </port>
149
+ </output>
150
+ </layer>
151
+ <layer id="10" name="self.2.weight" type="Const" version="opset1">
152
+ <data element_type="i8" shape="3072, 3072" offset="12601344" size="9437184" />
153
+ <output>
154
+ <port id="0" precision="I8">
155
+ <dim>3072</dim>
156
+ <dim>3072</dim>
157
+ </port>
158
+ </output>
159
+ </layer>
160
+ <layer id="11" name="Convert_1500505" type="Convert" version="opset1">
161
+ <data destination_type="f16" />
162
+ <input>
163
+ <port id="0" precision="I8">
164
+ <dim>3072</dim>
165
+ <dim>3072</dim>
166
+ </port>
167
+ </input>
168
+ <output>
169
+ <port id="1" precision="FP16">
170
+ <dim>3072</dim>
171
+ <dim>3072</dim>
172
+ </port>
173
+ </output>
174
+ </layer>
175
+ <layer id="12" name="self.2.weight/scale" type="Const" version="opset1">
176
+ <data element_type="f16" shape="3072, 1" offset="22038528" size="6144" />
177
+ <output>
178
+ <port id="0" precision="FP16">
179
+ <dim>3072</dim>
180
+ <dim>1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="13" name="self.2.weight/fq_weights_1" type="Multiply" version="opset1">
185
+ <data auto_broadcast="numpy" />
186
+ <input>
187
+ <port id="0" precision="FP16">
188
+ <dim>3072</dim>
189
+ <dim>3072</dim>
190
+ </port>
191
+ <port id="1" precision="FP16">
192
+ <dim>3072</dim>
193
+ <dim>1</dim>
194
+ </port>
195
+ </input>
196
+ <output>
197
+ <port id="2" precision="FP16">
198
+ <dim>3072</dim>
199
+ <dim>3072</dim>
200
+ </port>
201
+ </output>
202
+ </layer>
203
+ <layer id="14" name="self.2.weight/fq_weights_1/convert" type="Convert" version="opset1">
204
+ <data destination_type="f32" />
205
+ <input>
206
+ <port id="0" precision="FP16">
207
+ <dim>3072</dim>
208
+ <dim>3072</dim>
209
+ </port>
210
+ </input>
211
+ <output>
212
+ <port id="1" precision="FP32">
213
+ <dim>3072</dim>
214
+ <dim>3072</dim>
215
+ </port>
216
+ </output>
217
+ </layer>
218
+ <layer id="15" name="__module.2/ov_ext::linear/MatMul" type="MatMul" version="opset1">
219
+ <data transpose_a="false" transpose_b="true" />
220
+ <input>
221
+ <port id="0" precision="FP32">
222
+ <dim>-1</dim>
223
+ <dim>-1</dim>
224
+ <dim>3072</dim>
225
+ </port>
226
+ <port id="1" precision="FP32">
227
+ <dim>3072</dim>
228
+ <dim>3072</dim>
229
+ </port>
230
+ </input>
231
+ <output>
232
+ <port id="2" precision="FP32">
233
+ <dim>-1</dim>
234
+ <dim>-1</dim>
235
+ <dim>3072</dim>
236
+ </port>
237
+ </output>
238
+ </layer>
239
+ <layer id="16" name="Constant_167807" type="Const" version="opset1">
240
+ <data element_type="f32" shape="1, 1, 3072" offset="22044672" size="12288" />
241
+ <output>
242
+ <port id="0" precision="FP32">
243
+ <dim>1</dim>
244
+ <dim>1</dim>
245
+ <dim>3072</dim>
246
+ </port>
247
+ </output>
248
+ </layer>
249
+ <layer id="17" name="__module.2/ov_ext::linear/Add" type="Add" version="opset1">
250
+ <data auto_broadcast="numpy" />
251
+ <input>
252
+ <port id="0" precision="FP32">
253
+ <dim>-1</dim>
254
+ <dim>-1</dim>
255
+ <dim>3072</dim>
256
+ </port>
257
+ <port id="1" precision="FP32">
258
+ <dim>1</dim>
259
+ <dim>1</dim>
260
+ <dim>3072</dim>
261
+ </port>
262
+ </input>
263
+ <output>
264
+ <port id="2" precision="FP32" names="last_hidden_state">
265
+ <dim>-1</dim>
266
+ <dim>-1</dim>
267
+ <dim>3072</dim>
268
+ </port>
269
+ </output>
270
+ </layer>
271
+ <layer id="18" name="Result_165784" type="Result" version="opset1" output_names="last_hidden_state">
272
+ <input>
273
+ <port id="0" precision="FP32">
274
+ <dim>-1</dim>
275
+ <dim>-1</dim>
276
+ <dim>3072</dim>
277
+ </port>
278
+ </input>
279
+ </layer>
280
+ </layers>
281
+ <edges>
282
+ <edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
283
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
284
+ <edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
285
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
286
+ <edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
287
+ <edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
288
+ <edge from-layer="6" from-port="2" to-layer="8" to-port="0" />
289
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="1" />
290
+ <edge from-layer="8" from-port="2" to-layer="9" to-port="0" />
291
+ <edge from-layer="9" from-port="1" to-layer="15" to-port="0" />
292
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="0" />
293
+ <edge from-layer="11" from-port="1" to-layer="13" to-port="0" />
294
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
295
+ <edge from-layer="13" from-port="2" to-layer="14" to-port="0" />
296
+ <edge from-layer="14" from-port="1" to-layer="15" to-port="1" />
297
+ <edge from-layer="15" from-port="2" to-layer="17" to-port="0" />
298
+ <edge from-layer="16" from-port="0" to-layer="17" to-port="1" />
299
+ <edge from-layer="17" from-port="2" to-layer="18" to-port="0" />
300
+ </edges>
301
+ <rt_info>
302
+ <Runtime_version value="2025.4.1-20426-82bbf0292c5-releases/2025/4" />
303
+ <conversion_parameters>
304
+ <framework value="pytorch" />
305
+ <is_python_object value="True" />
306
+ </conversion_parameters>
307
+ <nncf>
308
+ <friendly_names_were_updated value="True" />
309
+ <version value="2.19.0" />
310
+ <weight_compression>
311
+ <advanced_parameters value="{'statistics_path': None, 'lora_adapter_rank': 256, 'group_size_fallback_mode': 'error', 'min_adjusted_group_size': 32, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100, 'prefer_data_aware_scaling': True}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}, 'backend_params': {}, 'codebook': None}" />
312
+ <all_layers value="False" />
313
+ <awq value="False" />
314
+ <backup_mode value="int8_asym" />
315
+ <compression_format value="dequantize" />
316
+ <gptq value="False" />
317
+ <group_size value="-1" />
318
+ <ignored_scope value="[]" />
319
+ <lora_correction value="False" />
320
+ <mode value="int8_sym" />
321
+ <ratio value="1.0" />
322
+ <scale_estimation value="False" />
323
+ <sensitivity_metric value="weight_quantization_error" />
324
+ </weight_compression>
325
+ </nncf>
326
+ <optimum>
327
+ <nncf_version value="2.19.0" />
328
+ <optimum_intel_version value="1.27.0.dev0+132f70d" />
329
+ <optimum_version value="2.1.0.dev0" />
330
+ <pytorch_version value="2.9.1+cpu" />
331
+ <transformers_version value="4.51.0" />
332
+ </optimum>
333
+ </rt_info>
334
+ </net>
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VImageProcessor",
4
+ "AutoProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VProcessor"
5
+ },
6
+ "do_convert_rgb": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Phi3VImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "num_crops": 4,
19
+ "num_img_tokens": 144,
20
+ "processor_class": "Phi3VProcessor"
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|system|>",
4
+ "<|end|>",
5
+ "<|user|>",
6
+ "<|end|>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,414 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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>",
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": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
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": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|placeholder7|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": true,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|placeholder8|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": true,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|placeholder9|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": true,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|placeholder10|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": true,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|placeholder11|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": true,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|placeholder12|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": true,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|placeholder13|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": true,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|placeholder14|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": true,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|placeholder15|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": true,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|placeholder16|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": true,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|placeholder17|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": true,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|placeholder18|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": true,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|placeholder19|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": true,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|placeholder20|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": true,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|placeholder21|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": true,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|placeholder22|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": true,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|placeholder23|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": true,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|placeholder24|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": true,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|placeholder25|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": true,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|placeholder26|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": true,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|placeholder27|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": true,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|placeholder28|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": true,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|placeholder29|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": true,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|placeholder30|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": true,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|placeholder31|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": true,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|placeholder32|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": true,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|placeholder33|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": true,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "32038": {
335
+ "content": "<|placeholder34|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": true,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "32039": {
343
+ "content": "<|placeholder35|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": true,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "32040": {
351
+ "content": "<|placeholder36|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": true,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "32041": {
359
+ "content": "<|placeholder37|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": true,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "32042": {
367
+ "content": "<|placeholder38|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": true,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "32043": {
375
+ "content": "<|placeholder39|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": true,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "32044": {
383
+ "content": "<|image|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": true,
387
+ "single_word": false,
388
+ "special": true
389
+ }
390
+ },
391
+ "additional_special_tokens": [
392
+ "<|system|>",
393
+ "<|end|>",
394
+ "<|user|>",
395
+ "<|end|>"
396
+ ],
397
+ "auto_map": {
398
+ "AutoProcessor": "microsoft/Phi-3.5-vision-instruct--processing_phi3_v.Phi3VProcessor"
399
+ },
400
+ "bos_token": "<s>",
401
+ "chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
402
+ "clean_up_tokenization_spaces": false,
403
+ "eos_token": "<|endoftext|>",
404
+ "extra_special_tokens": {},
405
+ "legacy": false,
406
+ "model_max_length": 131072,
407
+ "pad_token": "<|endoftext|>",
408
+ "padding_side": "right",
409
+ "processor_class": "Phi3VProcessor",
410
+ "sp_model_kwargs": {},
411
+ "tokenizer_class": "LlamaTokenizerFast",
412
+ "unk_token": "<unk>",
413
+ "use_default_system_prompt": false
414
+ }