Hugging Face's logo

helenai
/
Qwen2-VL-2B-Instruct-ov-int4

OpenVINO
qwen2_vl
Model card Files Community
helenai commited on
Commit
8c0145a
·
1 Parent(s): 06bc63c

Add INT4 model

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. chat_template.json +3 -0
  4. config.json +48 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. openvino_config.json +28 -0
  8. openvino_detokenizer.bin +3 -0
  9. openvino_detokenizer.xml +284 -0
  10. openvino_language_model.bin +3 -0
  11. openvino_language_model.xml +0 -0
  12. openvino_text_embeddings_model.bin +3 -0
  13. openvino_text_embeddings_model.xml +173 -0
  14. openvino_tokenizer.bin +3 -0
  15. openvino_tokenizer.xml +736 -0
  16. openvino_vision_embeddings_merger_model.bin +3 -0
  17. openvino_vision_embeddings_merger_model.xml +0 -0
  18. openvino_vision_embeddings_model.bin +3 -0
  19. openvino_vision_embeddings_model.xml +245 -0
  20. preprocessor_config.json +29 -0
  21. special_tokens_map.json +31 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +144 -0
  24. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/tmpie9m1m7x",
3
+ "architectures": [
4
+ "Qwen2VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8960,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 2,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.45.0",
35
+ "use_cache": true,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "hidden_size": 1536,
40
+ "in_chans": 3,
41
+ "model_type": "qwen2_vl",
42
+ "spatial_patch_size": 14
43
+ },
44
+ "vision_end_token_id": 151653,
45
+ "vision_start_token_id": 151652,
46
+ "vision_token_id": 151654,
47
+ "vocab_size": 151936
48
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.45.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "compression": null,
3
+ "dtype": "int4",
4
+ "input_info": null,
5
+ "optimum_version": "1.24.0.dev0",
6
+ "quantization_config": {
7
+ "all_layers": null,
8
+ "backup_precision": null,
9
+ "bits": 4,
10
+ "dataset": "contextual",
11
+ "gptq": null,
12
+ "group_size": 128,
13
+ "ignored_scope": null,
14
+ "lora_correction": null,
15
+ "num_samples": 32,
16
+ "processor": null,
17
+ "quant_method": "awq",
18
+ "ratio": 1.0,
19
+ "scale_estimation": null,
20
+ "sensitivity_metric": null,
21
+ "sym": false,
22
+ "tokenizer": null,
23
+ "trust_remote_code": true,
24
+ "weight_format": "int4"
25
+ },
26
+ "save_onnx_model": false,
27
+ "transformers_version": "4.45.0"
28
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb12801a6a777afe2a420b1703b87b70f91ca0b62618a612fd7e2f86c357aaf1
3
+ size 1582874
openvino_detokenizer.xml ADDED
@@ -0,0 +1,284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_108" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_108">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_124" 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_83" type="Const" version="opset1">
29
+ <data element_type="u8" shape="1582798" offset="0" size="1582798" />
30
+ <output>
31
+ <port id="0" precision="U8">
32
+ <dim>1582798</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="StringTensorUnpack_84" type="StringTensorUnpack" version="extension">
37
+ <data mode="begins_ends" />
38
+ <input>
39
+ <port id="0" precision="U8">
40
+ <dim>1582798</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I32">
45
+ <dim>-1</dim>
46
+ </port>
47
+ <port id="2" precision="I32">
48
+ <dim>-1</dim>
49
+ </port>
50
+ <port id="3" precision="U8">
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="Constant_112" type="Const" version="opset1">
56
+ <data element_type="i32" shape="14" offset="1582798" size="56" />
57
+ <output>
58
+ <port id="0" precision="I32">
59
+ <dim>14</dim>
60
+ </port>
61
+ </output>
62
+ </layer>
63
+ <layer id="5" name="Constant_110" type="Const" version="opset1">
64
+ <data element_type="i32" shape="1" offset="1582854" size="4" />
65
+ <output>
66
+ <port id="0" precision="I32">
67
+ <dim>1</dim>
68
+ </port>
69
+ </output>
70
+ </layer>
71
+ <layer id="6" name="Constant_109" type="Const" version="opset1">
72
+ <data element_type="i32" shape="1" offset="1582858" size="4" />
73
+ <output>
74
+ <port id="0" precision="I32">
75
+ <dim>1</dim>
76
+ </port>
77
+ </output>
78
+ </layer>
79
+ <layer id="7" name="Constant_111" type="Const" version="opset1">
80
+ <data element_type="i32" shape="1" offset="1582862" size="4" />
81
+ <output>
82
+ <port id="0" precision="I32">
83
+ <dim>1</dim>
84
+ </port>
85
+ </output>
86
+ </layer>
87
+ <layer id="8" name="Constant_114" type="Const" version="opset1">
88
+ <data element_type="i64" shape="1" offset="1582866" size="8" />
89
+ <output>
90
+ <port id="0" precision="I64">
91
+ <dim>1</dim>
92
+ </port>
93
+ </output>
94
+ </layer>
95
+ <layer id="9" name="Slice_113" type="Slice" version="opset8">
96
+ <input>
97
+ <port id="0" precision="I32">
98
+ <dim>14</dim>
99
+ </port>
100
+ <port id="1" precision="I32">
101
+ <dim>1</dim>
102
+ </port>
103
+ <port id="2" precision="I32">
104
+ <dim>1</dim>
105
+ </port>
106
+ <port id="3" precision="I32">
107
+ <dim>1</dim>
108
+ </port>
109
+ <port id="4" precision="I64">
110
+ <dim>1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="5" precision="I32">
115
+ <dim>14</dim>
116
+ </port>
117
+ </output>
118
+ </layer>
119
+ <layer id="10" name="VocabDecoder_115" type="VocabDecoder" version="extension">
120
+ <data skip_tokens="" />
121
+ <input>
122
+ <port id="0" precision="I32">
123
+ <dim>-1</dim>
124
+ <dim>-1</dim>
125
+ </port>
126
+ <port id="1" precision="I32">
127
+ <dim>-1</dim>
128
+ </port>
129
+ <port id="2" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ <port id="3" precision="U8">
133
+ <dim>-1</dim>
134
+ </port>
135
+ <port id="4" precision="I32">
136
+ <dim>14</dim>
137
+ </port>
138
+ </input>
139
+ <output>
140
+ <port id="5" precision="I32">
141
+ <dim>-1</dim>
142
+ </port>
143
+ <port id="6" precision="I32">
144
+ <dim>-1</dim>
145
+ </port>
146
+ <port id="7" precision="I32">
147
+ <dim>-1</dim>
148
+ </port>
149
+ <port id="8" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ <port id="9" precision="U8">
153
+ <dim>-1</dim>
154
+ </port>
155
+ </output>
156
+ </layer>
157
+ <layer id="11" name="FuzeRagged_116" type="FuzeRagged" version="extension">
158
+ <input>
159
+ <port id="0" precision="I32">
160
+ <dim>-1</dim>
161
+ </port>
162
+ <port id="1" precision="I32">
163
+ <dim>-1</dim>
164
+ </port>
165
+ <port id="2" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ <port id="3" precision="I32">
169
+ <dim>-1</dim>
170
+ </port>
171
+ </input>
172
+ <output>
173
+ <port id="4" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="5" precision="I32">
177
+ <dim>-1</dim>
178
+ </port>
179
+ </output>
180
+ </layer>
181
+ <layer id="12" name="UTF8Validate_117" type="UTF8Validate" version="extension">
182
+ <data replace_mode="true" />
183
+ <input>
184
+ <port id="0" precision="I32">
185
+ <dim>-1</dim>
186
+ </port>
187
+ <port id="1" precision="I32">
188
+ <dim>-1</dim>
189
+ </port>
190
+ <port id="2" precision="U8">
191
+ <dim>-1</dim>
192
+ </port>
193
+ </input>
194
+ <output>
195
+ <port id="3" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="4" precision="I32">
199
+ <dim>-1</dim>
200
+ </port>
201
+ <port id="5" precision="U8">
202
+ <dim>-1</dim>
203
+ </port>
204
+ </output>
205
+ </layer>
206
+ <layer id="13" name="StringTensorPack_118" type="StringTensorPack" version="extension">
207
+ <data mode="begins_ends" />
208
+ <input>
209
+ <port id="0" precision="I32">
210
+ <dim>-1</dim>
211
+ </port>
212
+ <port id="1" precision="I32">
213
+ <dim>-1</dim>
214
+ </port>
215
+ <port id="2" precision="U8">
216
+ <dim>-1</dim>
217
+ </port>
218
+ </input>
219
+ <output>
220
+ <port id="3" precision="STRING" names="string_output">
221
+ <dim>-1</dim>
222
+ </port>
223
+ </output>
224
+ </layer>
225
+ <layer id="14" name="Result_119" type="Result" version="opset1">
226
+ <input>
227
+ <port id="0" precision="STRING">
228
+ <dim>-1</dim>
229
+ </port>
230
+ </input>
231
+ </layer>
232
+ </layers>
233
+ <edges>
234
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
235
+ <edge from-layer="1" from-port="1" to-layer="10" to-port="0" />
236
+ <edge from-layer="2" from-port="0" to-layer="3" to-port="0" />
237
+ <edge from-layer="3" from-port="1" to-layer="10" to-port="1" />
238
+ <edge from-layer="3" from-port="2" to-layer="10" to-port="2" />
239
+ <edge from-layer="3" from-port="3" to-layer="10" to-port="3" />
240
+ <edge from-layer="4" from-port="0" to-layer="9" to-port="0" />
241
+ <edge from-layer="5" from-port="0" to-layer="9" to-port="1" />
242
+ <edge from-layer="6" from-port="0" to-layer="9" to-port="2" />
243
+ <edge from-layer="7" from-port="0" to-layer="9" to-port="3" />
244
+ <edge from-layer="8" from-port="0" to-layer="9" to-port="4" />
245
+ <edge from-layer="9" from-port="5" to-layer="10" to-port="4" />
246
+ <edge from-layer="10" from-port="5" to-layer="11" to-port="0" />
247
+ <edge from-layer="10" from-port="6" to-layer="11" to-port="1" />
248
+ <edge from-layer="10" from-port="7" to-layer="11" to-port="2" />
249
+ <edge from-layer="10" from-port="8" to-layer="11" to-port="3" />
250
+ <edge from-layer="10" from-port="9" to-layer="12" to-port="2" />
251
+ <edge from-layer="11" from-port="4" to-layer="12" to-port="0" />
252
+ <edge from-layer="11" from-port="5" to-layer="12" to-port="1" />
253
+ <edge from-layer="12" from-port="3" to-layer="13" to-port="0" />
254
+ <edge from-layer="12" from-port="4" to-layer="13" to-port="1" />
255
+ <edge from-layer="12" from-port="5" to-layer="13" to-port="2" />
256
+ <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
257
+ </edges>
258
+ <rt_info>
259
+ <add_attention_mask value="True" />
260
+ <add_prefix_space />
261
+ <add_special_tokens value="True" />
262
+ <chat_template value="{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;{% endif %}&lt;|im_start|>{{ message['role'] }}&#10;{% if message['content'] is string %}{{ message['content'] }}&lt;|im_end|>&#10;{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}&lt;|vision_start|>&lt;|image_pad|>&lt;|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}&lt;|vision_start|>&lt;|video_pad|>&lt;|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}&lt;|im_end|>&#10;{% endif %}{% endfor %}{% if add_generation_prompt %}&lt;|im_start|>assistant&#10;{% endif %}" />
263
+ <clean_up_tokenization_spaces />
264
+ <detokenizer_input_type value="i64" />
265
+ <eos_token_id value="151645" />
266
+ <handle_special_tokens_with_re value="False" />
267
+ <number_of_inputs value="1" />
268
+ <openvino_tokenizers_version value="2025.1.0.0.dev20250123" />
269
+ <openvino_version value="2025.1.0.dev20250123" />
270
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
271
+ <pad_token_id value="151643" />
272
+ <sentencepiece_version value="0.2.0" />
273
+ <skip_special_tokens value="True" />
274
+ <streaming_detokenizer value="False" />
275
+ <tiktoken_version value="0.8.0" />
276
+ <tokenizer_output_type value="i64" />
277
+ <tokenizers_version value="0.20.1" />
278
+ <transformers_version value="4.45.0" />
279
+ <use_max_padding value="False" />
280
+ <use_sentencepiece_backend value="True" />
281
+ <utf8_replace_mode value="replace" />
282
+ <with_detokenizer value="True" />
283
+ </rt_info>
284
+ </net>
openvino_language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ee99cee04ce846520c36ff222c61901b88518fe4af7db5e9e155bcd810d2c5
3
+ size 915097340
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 sha256:5ac0d0b3a3812b10a17b0f3643d21b23bd7ec8e41e70bc279eefbeeeee4ebbb7
3
+ size 233677572
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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="151936, 1536" offset="0" size="233373696" />
15
+ <output>
16
+ <port id="0" precision="I8">
17
+ <dim>151936</dim>
18
+ <dim>1536</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="Convert_290867" type="Convert" version="opset1">
23
+ <data destination_type="f16" />
24
+ <input>
25
+ <port id="0" precision="I8">
26
+ <dim>151936</dim>
27
+ <dim>1536</dim>
28
+ </port>
29
+ </input>
30
+ <output>
31
+ <port id="1" precision="FP16">
32
+ <dim>151936</dim>
33
+ <dim>1536</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="151936, 1" offset="233373696" size="303872" />
39
+ <output>
40
+ <port id="0" precision="FP16">
41
+ <dim>151936</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>151936</dim>
51
+ <dim>1536</dim>
52
+ </port>
53
+ <port id="1" precision="FP16">
54
+ <dim>151936</dim>
55
+ <dim>1</dim>
56
+ </port>
57
+ </input>
58
+ <output>
59
+ <port id="2" precision="FP16">
60
+ <dim>151936</dim>
61
+ <dim>1536</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>151936</dim>
70
+ <dim>1536</dim>
71
+ </port>
72
+ </input>
73
+ <output>
74
+ <port id="1" precision="FP32">
75
+ <dim>151936</dim>
76
+ <dim>1536</dim>
77
+ </port>
78
+ </output>
79
+ </layer>
80
+ <layer id="6" name="aten::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="aten::embedding/Constant" type="Const" version="opset1">
96
+ <data element_type="i32" shape="" offset="233677568" size="4" />
97
+ <output>
98
+ <port id="0" precision="I32" />
99
+ </output>
100
+ </layer>
101
+ <layer id="8" name="aten::embedding/Gather" type="Gather" version="opset8">
102
+ <data batch_dims="0" />
103
+ <input>
104
+ <port id="0" precision="FP32">
105
+ <dim>151936</dim>
106
+ <dim>1536</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>1536</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="9" name="Result_161867" type="Result" version="opset1">
123
+ <input>
124
+ <port id="0" precision="FP32">
125
+ <dim>-1</dim>
126
+ <dim>-1</dim>
127
+ <dim>1536</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="2025.1.0-17990-dc1d9675cbf" />
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
+ <weight_compression>
152
+ <advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, '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}}" />
153
+ <all_layers value="False" />
154
+ <awq value="False" />
155
+ <backup_mode value="int8_asym" />
156
+ <gptq value="False" />
157
+ <group_size value="-1" />
158
+ <ignored_scope value="[]" />
159
+ <lora_correction value="False" />
160
+ <mode value="int8_sym" />
161
+ <ratio value="1.0" />
162
+ <scale_estimation value="False" />
163
+ <sensitivity_metric value="weight_quantization_error" />
164
+ </weight_compression>
165
+ </nncf>
166
+ <optimum>
167
+ <optimum_intel_version value="1.22.0.dev0+753f84d" />
168
+ <optimum_version value="1.24.0.dev0" />
169
+ <pytorch_version value="2.5.0+cpu" />
170
+ <transformers_version value="4.45.0" />
171
+ </optimum>
172
+ </rt_info>
173
+ </net>
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9685758099e61f824d507e047d2b6210e944fe1b5a36c91e397ebe2c0817545
3
+ size 3770364
openvino_tokenizer.xml ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_7" type="Const" version="opset1">
13
+ <data element_type="i64" shape="" offset="0" size="8" />
14
+ <output>
15
+ <port id="0" precision="I64" />
16
+ </output>
17
+ </layer>
18
+ <layer id="2" name="StringTensorUnpack_2" type="StringTensorUnpack" version="extension">
19
+ <data mode="begins_ends" />
20
+ <input>
21
+ <port id="0" precision="STRING">
22
+ <dim>-1</dim>
23
+ </port>
24
+ </input>
25
+ <output>
26
+ <port id="1" precision="I32">
27
+ <dim>-1</dim>
28
+ </port>
29
+ <port id="2" precision="I32">
30
+ <dim>-1</dim>
31
+ </port>
32
+ <port id="3" precision="U8">
33
+ <dim>-1</dim>
34
+ </port>
35
+ </output>
36
+ </layer>
37
+ <layer id="3" name="ShapeOf_3" type="ShapeOf" version="opset3">
38
+ <data output_type="i64" />
39
+ <input>
40
+ <port id="0" precision="I32">
41
+ <dim>-1</dim>
42
+ </port>
43
+ </input>
44
+ <output>
45
+ <port id="1" precision="I64">
46
+ <dim>1</dim>
47
+ </port>
48
+ </output>
49
+ </layer>
50
+ <layer id="4" name="Constant_4" type="Const" version="opset1">
51
+ <data element_type="i64" shape="" offset="0" size="8" />
52
+ <output>
53
+ <port id="0" precision="I64" />
54
+ </output>
55
+ </layer>
56
+ <layer id="5" name="Constant_5" type="Const" version="opset1">
57
+ <data element_type="i64" shape="" offset="0" size="8" />
58
+ <output>
59
+ <port id="0" precision="I64" />
60
+ </output>
61
+ </layer>
62
+ <layer id="6" name="Gather_6" type="Gather" version="opset8">
63
+ <data batch_dims="0" />
64
+ <input>
65
+ <port id="0" precision="I64">
66
+ <dim>1</dim>
67
+ </port>
68
+ <port id="1" precision="I64" />
69
+ <port id="2" precision="I64" />
70
+ </input>
71
+ <output>
72
+ <port id="3" precision="I64" />
73
+ </output>
74
+ </layer>
75
+ <layer id="7" name="Constant_8" 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="8" name="Range_9" type="Range" version="opset4">
82
+ <data output_type="i32" />
83
+ <input>
84
+ <port id="0" precision="I64" />
85
+ <port id="1" precision="I64" />
86
+ <port id="2" precision="I64" />
87
+ </input>
88
+ <output>
89
+ <port id="3" precision="I32">
90
+ <dim>-1</dim>
91
+ </port>
92
+ </output>
93
+ </layer>
94
+ <layer id="9" name="Constant_10" type="Const" version="opset1">
95
+ <data element_type="i64" shape="" offset="8" size="8" />
96
+ <output>
97
+ <port id="0" precision="I64" />
98
+ </output>
99
+ </layer>
100
+ <layer id="10" name="Constant_11" type="Const" version="opset1">
101
+ <data element_type="i64" shape="" offset="8" size="8" />
102
+ <output>
103
+ <port id="0" precision="I64" />
104
+ </output>
105
+ </layer>
106
+ <layer id="11" name="Add_12" type="Add" version="opset1">
107
+ <data auto_broadcast="numpy" />
108
+ <input>
109
+ <port id="0" precision="I64" />
110
+ <port id="1" precision="I64" />
111
+ </input>
112
+ <output>
113
+ <port id="2" precision="I64" />
114
+ </output>
115
+ </layer>
116
+ <layer id="12" name="Constant_13" type="Const" version="opset1">
117
+ <data element_type="i64" shape="" offset="8" size="8" />
118
+ <output>
119
+ <port id="0" precision="I64" />
120
+ </output>
121
+ </layer>
122
+ <layer id="13" name="Range_14" type="Range" version="opset4">
123
+ <data output_type="i32" />
124
+ <input>
125
+ <port id="0" precision="I64" />
126
+ <port id="1" precision="I64" />
127
+ <port id="2" precision="I64" />
128
+ </input>
129
+ <output>
130
+ <port id="3" precision="I32">
131
+ <dim>-1</dim>
132
+ </port>
133
+ </output>
134
+ </layer>
135
+ <layer id="14" name="Constant_76" type="Const" version="opset1">
136
+ <data element_type="u8" shape="290" offset="16" size="290" />
137
+ <output>
138
+ <port id="0" precision="U8">
139
+ <dim>290</dim>
140
+ </port>
141
+ </output>
142
+ </layer>
143
+ <layer id="15" name="SpecialTokensSplit_77" type="SpecialTokensSplit" version="extension">
144
+ <input>
145
+ <port id="0" precision="I32">
146
+ <dim>-1</dim>
147
+ </port>
148
+ <port id="1" precision="I32">
149
+ <dim>-1</dim>
150
+ </port>
151
+ <port id="2" precision="I32">
152
+ <dim>-1</dim>
153
+ </port>
154
+ <port id="3" precision="I32">
155
+ <dim>-1</dim>
156
+ </port>
157
+ <port id="4" precision="U8">
158
+ <dim>-1</dim>
159
+ </port>
160
+ <port id="5" precision="U8">
161
+ <dim>290</dim>
162
+ </port>
163
+ </input>
164
+ <output>
165
+ <port id="6" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ <port id="7" precision="I32">
169
+ <dim>-1</dim>
170
+ </port>
171
+ <port id="8" precision="I32">
172
+ <dim>-1</dim>
173
+ </port>
174
+ <port id="9" precision="I32">
175
+ <dim>-1</dim>
176
+ </port>
177
+ <port id="10" precision="U8">
178
+ <dim>-1</dim>
179
+ </port>
180
+ <port id="11" precision="BOOL">
181
+ <dim>-1</dim>
182
+ </port>
183
+ </output>
184
+ </layer>
185
+ <layer id="16" name="NormalizeUnicode_78" type="NormalizeUnicode" version="extension">
186
+ <data normalization_form="NFC" />
187
+ <input>
188
+ <port id="0" precision="I32">
189
+ <dim>-1</dim>
190
+ </port>
191
+ <port id="1" precision="I32">
192
+ <dim>-1</dim>
193
+ </port>
194
+ <port id="2" precision="U8">
195
+ <dim>-1</dim>
196
+ </port>
197
+ <port id="3" precision="BOOL">
198
+ <dim>-1</dim>
199
+ </port>
200
+ </input>
201
+ <output>
202
+ <port id="4" precision="I32">
203
+ <dim>-1</dim>
204
+ </port>
205
+ <port id="5" precision="I32">
206
+ <dim>-1</dim>
207
+ </port>
208
+ <port id="6" precision="U8">
209
+ <dim>-1</dim>
210
+ </port>
211
+ <port id="7" precision="BOOL">
212
+ <dim>-1</dim>
213
+ </port>
214
+ </output>
215
+ </layer>
216
+ <layer id="17" name="Constant_80" type="Const" version="opset1">
217
+ <data element_type="u8" shape="110" offset="306" size="110" />
218
+ <output>
219
+ <port id="0" precision="U8">
220
+ <dim>110</dim>
221
+ </port>
222
+ </output>
223
+ </layer>
224
+ <layer id="18" name="RegexSplit_81" type="RegexSplit" version="extension">
225
+ <data behaviour="isolate" invert="false" max_splits="-1" />
226
+ <input>
227
+ <port id="0" precision="I32">
228
+ <dim>-1</dim>
229
+ </port>
230
+ <port id="1" precision="I32">
231
+ <dim>-1</dim>
232
+ </port>
233
+ <port id="2" precision="I32">
234
+ <dim>-1</dim>
235
+ </port>
236
+ <port id="3" precision="I32">
237
+ <dim>-1</dim>
238
+ </port>
239
+ <port id="4" precision="U8">
240
+ <dim>-1</dim>
241
+ </port>
242
+ <port id="5" precision="BOOL">
243
+ <dim>-1</dim>
244
+ </port>
245
+ <port id="6" precision="U8">
246
+ <dim>110</dim>
247
+ </port>
248
+ </input>
249
+ <output>
250
+ <port id="7" precision="I32">
251
+ <dim>-1</dim>
252
+ </port>
253
+ <port id="8" precision="I32">
254
+ <dim>-1</dim>
255
+ </port>
256
+ <port id="9" precision="I32">
257
+ <dim>-1</dim>
258
+ </port>
259
+ <port id="10" precision="I32">
260
+ <dim>-1</dim>
261
+ </port>
262
+ <port id="11" precision="U8">
263
+ <dim>-1</dim>
264
+ </port>
265
+ <port id="12" precision="BOOL">
266
+ <dim>-1</dim>
267
+ </port>
268
+ </output>
269
+ </layer>
270
+ <layer id="19" name="Constant_83" type="Const" version="opset1">
271
+ <data element_type="u8" shape="1582798" offset="416" size="1582798" />
272
+ <output>
273
+ <port id="0" precision="U8">
274
+ <dim>1582798</dim>
275
+ </port>
276
+ </output>
277
+ </layer>
278
+ <layer id="20" name="StringTensorUnpack_84" type="StringTensorUnpack" version="extension">
279
+ <data mode="begins_ends" />
280
+ <input>
281
+ <port id="0" precision="U8">
282
+ <dim>1582798</dim>
283
+ </port>
284
+ </input>
285
+ <output>
286
+ <port id="1" precision="I32">
287
+ <dim>-1</dim>
288
+ </port>
289
+ <port id="2" precision="I32">
290
+ <dim>-1</dim>
291
+ </port>
292
+ <port id="3" precision="U8">
293
+ <dim>-1</dim>
294
+ </port>
295
+ </output>
296
+ </layer>
297
+ <layer id="21" name="Constant_89" type="Const" version="opset1">
298
+ <data element_type="u8" shape="1096915" offset="1583214" size="1096915" />
299
+ <output>
300
+ <port id="0" precision="U8">
301
+ <dim>1096915</dim>
302
+ </port>
303
+ </output>
304
+ </layer>
305
+ <layer id="22" name="StringTensorUnpack_90" type="StringTensorUnpack" version="extension">
306
+ <data mode="begins_ends" />
307
+ <input>
308
+ <port id="0" precision="U8">
309
+ <dim>1096915</dim>
310
+ </port>
311
+ </input>
312
+ <output>
313
+ <port id="1" precision="I32">
314
+ <dim>-1</dim>
315
+ </port>
316
+ <port id="2" precision="I32">
317
+ <dim>-1</dim>
318
+ </port>
319
+ <port id="3" precision="U8">
320
+ <dim>-1</dim>
321
+ </port>
322
+ </output>
323
+ </layer>
324
+ <layer id="23" name="Constant_92" type="Const" version="opset1">
325
+ <data element_type="u8" shape="1089910" offset="2680129" size="1089910" />
326
+ <output>
327
+ <port id="0" precision="U8">
328
+ <dim>1089910</dim>
329
+ </port>
330
+ </output>
331
+ </layer>
332
+ <layer id="24" name="StringTensorUnpack_93" type="StringTensorUnpack" version="extension">
333
+ <data mode="begins_ends" />
334
+ <input>
335
+ <port id="0" precision="U8">
336
+ <dim>1089910</dim>
337
+ </port>
338
+ </input>
339
+ <output>
340
+ <port id="1" precision="I32">
341
+ <dim>-1</dim>
342
+ </port>
343
+ <port id="2" precision="I32">
344
+ <dim>-1</dim>
345
+ </port>
346
+ <port id="3" precision="U8">
347
+ <dim>-1</dim>
348
+ </port>
349
+ </output>
350
+ </layer>
351
+ <layer id="25" name="Constant_86" type="Const" version="opset1">
352
+ <data element_type="u8" shape="257" offset="3770039" size="257" />
353
+ <output>
354
+ <port id="0" precision="U8">
355
+ <dim>257</dim>
356
+ </port>
357
+ </output>
358
+ </layer>
359
+ <layer id="26" name="StringTensorUnpack_87" type="StringTensorUnpack" version="extension">
360
+ <data mode="begins_ends" />
361
+ <input>
362
+ <port id="0" precision="U8">
363
+ <dim>257</dim>
364
+ </port>
365
+ </input>
366
+ <output>
367
+ <port id="1" precision="I32">
368
+ <dim>-1</dim>
369
+ </port>
370
+ <port id="2" precision="I32">
371
+ <dim>-1</dim>
372
+ </port>
373
+ <port id="3" precision="U8">
374
+ <dim>-1</dim>
375
+ </port>
376
+ </output>
377
+ </layer>
378
+ <layer id="27" name="Constant_94" type="Const" version="opset1">
379
+ <data element_type="i32" shape="14" offset="3770296" size="56" />
380
+ <output>
381
+ <port id="0" precision="I32">
382
+ <dim>14</dim>
383
+ </port>
384
+ </output>
385
+ </layer>
386
+ <layer id="28" name="BPETokenizer_95" type="BPETokenizer" version="extension">
387
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
388
+ <input>
389
+ <port id="0" precision="I32">
390
+ <dim>-1</dim>
391
+ </port>
392
+ <port id="1" precision="I32">
393
+ <dim>-1</dim>
394
+ </port>
395
+ <port id="2" precision="I32">
396
+ <dim>-1</dim>
397
+ </port>
398
+ <port id="3" precision="I32">
399
+ <dim>-1</dim>
400
+ </port>
401
+ <port id="4" precision="U8">
402
+ <dim>-1</dim>
403
+ </port>
404
+ <port id="5" precision="I32">
405
+ <dim>-1</dim>
406
+ </port>
407
+ <port id="6" precision="I32">
408
+ <dim>-1</dim>
409
+ </port>
410
+ <port id="7" precision="U8">
411
+ <dim>-1</dim>
412
+ </port>
413
+ <port id="8" precision="I32">
414
+ <dim>-1</dim>
415
+ </port>
416
+ <port id="9" precision="I32">
417
+ <dim>-1</dim>
418
+ </port>
419
+ <port id="10" precision="U8">
420
+ <dim>-1</dim>
421
+ </port>
422
+ <port id="11" precision="I32">
423
+ <dim>-1</dim>
424
+ </port>
425
+ <port id="12" precision="I32">
426
+ <dim>-1</dim>
427
+ </port>
428
+ <port id="13" precision="U8">
429
+ <dim>-1</dim>
430
+ </port>
431
+ <port id="14" precision="I32">
432
+ <dim>-1</dim>
433
+ </port>
434
+ <port id="15" precision="I32">
435
+ <dim>-1</dim>
436
+ </port>
437
+ <port id="16" precision="U8">
438
+ <dim>-1</dim>
439
+ </port>
440
+ <port id="17" precision="I32">
441
+ <dim>14</dim>
442
+ </port>
443
+ </input>
444
+ <output>
445
+ <port id="18" precision="I32">
446
+ <dim>-1</dim>
447
+ </port>
448
+ <port id="19" precision="I32">
449
+ <dim>-1</dim>
450
+ </port>
451
+ <port id="20" precision="I32">
452
+ <dim>-1</dim>
453
+ </port>
454
+ </output>
455
+ </layer>
456
+ <layer id="29" name="Subtract_96" type="Subtract" version="opset1">
457
+ <data auto_broadcast="numpy" />
458
+ <input>
459
+ <port id="0" precision="I32">
460
+ <dim>-1</dim>
461
+ </port>
462
+ <port id="1" precision="I32">
463
+ <dim>-1</dim>
464
+ </port>
465
+ </input>
466
+ <output>
467
+ <port id="2" precision="I32">
468
+ <dim>-1</dim>
469
+ </port>
470
+ </output>
471
+ </layer>
472
+ <layer id="30" name="Constant_97" type="Const" version="opset1">
473
+ <data element_type="i32" shape="" offset="3770352" size="4" />
474
+ <output>
475
+ <port id="0" precision="I32" />
476
+ </output>
477
+ </layer>
478
+ <layer id="31" name="Minimum_98" type="Minimum" version="opset1">
479
+ <data auto_broadcast="numpy" />
480
+ <input>
481
+ <port id="0" precision="I32">
482
+ <dim>-1</dim>
483
+ </port>
484
+ <port id="1" precision="I32" />
485
+ </input>
486
+ <output>
487
+ <port id="2" precision="I32">
488
+ <dim>-1</dim>
489
+ </port>
490
+ </output>
491
+ </layer>
492
+ <layer id="32" name="Add_99" type="Add" version="opset1">
493
+ <data auto_broadcast="numpy" />
494
+ <input>
495
+ <port id="0" precision="I32">
496
+ <dim>-1</dim>
497
+ </port>
498
+ <port id="1" precision="I32">
499
+ <dim>-1</dim>
500
+ </port>
501
+ </input>
502
+ <output>
503
+ <port id="2" precision="I32">
504
+ <dim>-1</dim>
505
+ </port>
506
+ </output>
507
+ </layer>
508
+ <layer id="33" name="Subtract_100" type="Subtract" version="opset1">
509
+ <data auto_broadcast="numpy" />
510
+ <input>
511
+ <port id="0" precision="I32">
512
+ <dim>-1</dim>
513
+ </port>
514
+ <port id="1" precision="I32">
515
+ <dim>-1</dim>
516
+ </port>
517
+ </input>
518
+ <output>
519
+ <port id="2" precision="I32">
520
+ <dim>-1</dim>
521
+ </port>
522
+ </output>
523
+ </layer>
524
+ <layer id="34" name="Constant_101" type="Const" version="opset1">
525
+ <data element_type="i32" shape="" offset="3770356" size="4" />
526
+ <output>
527
+ <port id="0" precision="I32" />
528
+ </output>
529
+ </layer>
530
+ <layer id="35" name="ReduceMax_102" type="ReduceMax" version="opset1">
531
+ <data keep_dims="false" />
532
+ <input>
533
+ <port id="0" precision="I32">
534
+ <dim>-1</dim>
535
+ </port>
536
+ <port id="1" precision="I32" />
537
+ </input>
538
+ <output>
539
+ <port id="2" precision="I32" />
540
+ </output>
541
+ </layer>
542
+ <layer id="36" name="Constant_103" type="Const" version="opset1">
543
+ <data element_type="i32" shape="" offset="3770360" size="4" />
544
+ <output>
545
+ <port id="0" precision="I32" />
546
+ </output>
547
+ </layer>
548
+ <layer id="37" name="RaggedToDense_104" type="RaggedToDense" version="extension">
549
+ <data pad_right="false" />
550
+ <input>
551
+ <port id="0" precision="I32">
552
+ <dim>-1</dim>
553
+ </port>
554
+ <port id="1" precision="I32">
555
+ <dim>-1</dim>
556
+ </port>
557
+ <port id="2" precision="I32">
558
+ <dim>-1</dim>
559
+ </port>
560
+ <port id="3" precision="I32" />
561
+ <port id="4" precision="I32" />
562
+ </input>
563
+ <output>
564
+ <port id="5" precision="I32">
565
+ <dim>-1</dim>
566
+ <dim>-1</dim>
567
+ </port>
568
+ <port id="6" precision="BOOL">
569
+ <dim>-1</dim>
570
+ <dim>-1</dim>
571
+ </port>
572
+ </output>
573
+ </layer>
574
+ <layer id="38" name="Convert_105" type="Convert" version="opset1">
575
+ <data destination_type="i32" />
576
+ <input>
577
+ <port id="0" precision="BOOL">
578
+ <dim>-1</dim>
579
+ <dim>-1</dim>
580
+ </port>
581
+ </input>
582
+ <output>
583
+ <port id="1" precision="I32">
584
+ <dim>-1</dim>
585
+ <dim>-1</dim>
586
+ </port>
587
+ </output>
588
+ </layer>
589
+ <layer id="39" name="Convert_105.0" type="Convert" version="opset1">
590
+ <data destination_type="i64" />
591
+ <input>
592
+ <port id="0" precision="I32">
593
+ <dim>-1</dim>
594
+ <dim>-1</dim>
595
+ </port>
596
+ </input>
597
+ <output>
598
+ <port id="1" precision="I64" names="attention_mask">
599
+ <dim>-1</dim>
600
+ <dim>-1</dim>
601
+ </port>
602
+ </output>
603
+ </layer>
604
+ <layer id="41" name="RaggedToDense_104.0" type="Convert" version="opset1">
605
+ <data destination_type="i64" />
606
+ <input>
607
+ <port id="0" precision="I32">
608
+ <dim>-1</dim>
609
+ <dim>-1</dim>
610
+ </port>
611
+ </input>
612
+ <output>
613
+ <port id="1" precision="I64" names="input_ids">
614
+ <dim>-1</dim>
615
+ <dim>-1</dim>
616
+ </port>
617
+ </output>
618
+ </layer>
619
+ <layer id="42" name="Result_106" type="Result" version="opset1">
620
+ <input>
621
+ <port id="0" precision="I64">
622
+ <dim>-1</dim>
623
+ <dim>-1</dim>
624
+ </port>
625
+ </input>
626
+ </layer>
627
+ <layer id="40" name="Result_107" type="Result" version="opset1">
628
+ <input>
629
+ <port id="0" precision="I64">
630
+ <dim>-1</dim>
631
+ <dim>-1</dim>
632
+ </port>
633
+ </input>
634
+ </layer>
635
+ </layers>
636
+ <edges>
637
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
638
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
639
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
640
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
641
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
642
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
643
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
644
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
645
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
646
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
647
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
648
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
649
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
650
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
651
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
652
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
653
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
654
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
655
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
656
+ <edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
657
+ <edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
658
+ <edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
659
+ <edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
660
+ <edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
661
+ <edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
662
+ <edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
663
+ <edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
664
+ <edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
665
+ <edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
666
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
667
+ <edge from-layer="18" from-port="11" to-layer="28" to-port="4" />
668
+ <edge from-layer="18" from-port="10" to-layer="28" to-port="3" />
669
+ <edge from-layer="18" from-port="9" to-layer="28" to-port="2" />
670
+ <edge from-layer="18" from-port="8" to-layer="28" to-port="1" />
671
+ <edge from-layer="18" from-port="7" to-layer="28" to-port="0" />
672
+ <edge from-layer="19" from-port="0" to-layer="20" to-port="0" />
673
+ <edge from-layer="20" from-port="1" to-layer="28" to-port="5" />
674
+ <edge from-layer="20" from-port="2" to-layer="28" to-port="6" />
675
+ <edge from-layer="20" from-port="3" to-layer="28" to-port="7" />
676
+ <edge from-layer="21" from-port="0" to-layer="22" to-port="0" />
677
+ <edge from-layer="22" from-port="1" to-layer="28" to-port="8" />
678
+ <edge from-layer="22" from-port="2" to-layer="28" to-port="9" />
679
+ <edge from-layer="22" from-port="3" to-layer="28" to-port="10" />
680
+ <edge from-layer="23" from-port="0" to-layer="24" to-port="0" />
681
+ <edge from-layer="24" from-port="1" to-layer="28" to-port="11" />
682
+ <edge from-layer="24" from-port="2" to-layer="28" to-port="12" />
683
+ <edge from-layer="24" from-port="3" to-layer="28" to-port="13" />
684
+ <edge from-layer="25" from-port="0" to-layer="26" to-port="0" />
685
+ <edge from-layer="26" from-port="1" to-layer="28" to-port="14" />
686
+ <edge from-layer="26" from-port="2" to-layer="28" to-port="15" />
687
+ <edge from-layer="26" from-port="3" to-layer="28" to-port="16" />
688
+ <edge from-layer="27" from-port="0" to-layer="28" to-port="17" />
689
+ <edge from-layer="28" from-port="20" to-layer="37" to-port="2" />
690
+ <edge from-layer="28" from-port="18" to-layer="29" to-port="1" />
691
+ <edge from-layer="28" from-port="18" to-layer="37" to-port="0" />
692
+ <edge from-layer="28" from-port="18" to-layer="33" to-port="1" />
693
+ <edge from-layer="28" from-port="18" to-layer="32" to-port="0" />
694
+ <edge from-layer="28" from-port="19" to-layer="29" to-port="0" />
695
+ <edge from-layer="29" from-port="2" to-layer="31" to-port="0" />
696
+ <edge from-layer="30" from-port="0" to-layer="31" to-port="1" />
697
+ <edge from-layer="31" from-port="2" to-layer="32" to-port="1" />
698
+ <edge from-layer="32" from-port="2" to-layer="33" to-port="0" />
699
+ <edge from-layer="32" from-port="2" to-layer="37" to-port="1" />
700
+ <edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
701
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
702
+ <edge from-layer="35" from-port="2" to-layer="37" to-port="3" />
703
+ <edge from-layer="36" from-port="0" to-layer="37" to-port="4" />
704
+ <edge from-layer="37" from-port="6" to-layer="38" to-port="0" />
705
+ <edge from-layer="37" from-port="5" to-layer="41" to-port="0" />
706
+ <edge from-layer="38" from-port="1" to-layer="39" to-port="0" />
707
+ <edge from-layer="39" from-port="1" to-layer="40" to-port="0" />
708
+ <edge from-layer="41" from-port="1" to-layer="42" to-port="0" />
709
+ </edges>
710
+ <rt_info>
711
+ <add_attention_mask value="True" />
712
+ <add_prefix_space />
713
+ <add_special_tokens value="True" />
714
+ <chat_template value="{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;{% endif %}&lt;|im_start|>{{ message['role'] }}&#10;{% if message['content'] is string %}{{ message['content'] }}&lt;|im_end|>&#10;{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}&lt;|vision_start|>&lt;|image_pad|>&lt;|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}&lt;|vision_start|>&lt;|video_pad|>&lt;|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}&lt;|im_end|>&#10;{% endif %}{% endfor %}{% if add_generation_prompt %}&lt;|im_start|>assistant&#10;{% endif %}" />
715
+ <clean_up_tokenization_spaces />
716
+ <detokenizer_input_type value="i64" />
717
+ <eos_token_id value="151645" />
718
+ <handle_special_tokens_with_re value="False" />
719
+ <number_of_inputs value="1" />
720
+ <openvino_tokenizers_version value="2025.1.0.0.dev20250123" />
721
+ <openvino_version value="2025.1.0.dev20250123" />
722
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
723
+ <pad_token_id value="151643" />
724
+ <sentencepiece_version value="0.2.0" />
725
+ <skip_special_tokens value="True" />
726
+ <streaming_detokenizer value="False" />
727
+ <tiktoken_version value="0.8.0" />
728
+ <tokenizer_output_type value="i64" />
729
+ <tokenizers_version value="0.20.1" />
730
+ <transformers_version value="4.45.0" />
731
+ <use_max_padding value="False" />
732
+ <use_sentencepiece_backend value="True" />
733
+ <utf8_replace_mode value="replace" />
734
+ <with_detokenizer value="True" />
735
+ </rt_info>
736
+ </net>
openvino_vision_embeddings_merger_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ccbb6c98dbb0e567f3b7eb7f9648597c697337162638abe00d88783d0f19f9
3
+ size 666141892
openvino_vision_embeddings_merger_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
openvino_vision_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0e2e18d120c2c59281db9778ac9c27612a9a968fc3e76662e7d895674981bb
3
+ size 1507896
openvino_vision_embeddings_model.xml ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model3" version="11">
3
+ <layers>
4
+ <layer id="0" name="hidden_states" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="f32" />
6
+ <output>
7
+ <port id="0" precision="FP32" names="hidden_states">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Constant_71187" type="Const" version="opset1">
14
+ <data element_type="i64" shape="5" offset="0" size="40" />
15
+ <output>
16
+ <port id="0" precision="I64" names="8">
17
+ <dim>5</dim>
18
+ </port>
19
+ </output>
20
+ </layer>
21
+ <layer id="2" name="aten::view/Reshape" type="Reshape" version="opset1">
22
+ <data special_zero="false" />
23
+ <input>
24
+ <port id="0" precision="FP32">
25
+ <dim>-1</dim>
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="1" precision="I64">
29
+ <dim>5</dim>
30
+ </port>
31
+ </input>
32
+ <output>
33
+ <port id="2" precision="FP32" names="14,9,hidden_states">
34
+ <dim>-1</dim>
35
+ <dim>3</dim>
36
+ <dim>2</dim>
37
+ <dim>14</dim>
38
+ <dim>14</dim>
39
+ </port>
40
+ </output>
41
+ </layer>
42
+ <layer id="3" name="self.proj.weight" type="Const" version="opset1">
43
+ <data element_type="i8" shape="1280, 3, 2, 14, 14" offset="40" size="1505280" />
44
+ <output>
45
+ <port id="0" precision="I8">
46
+ <dim>1280</dim>
47
+ <dim>3</dim>
48
+ <dim>2</dim>
49
+ <dim>14</dim>
50
+ <dim>14</dim>
51
+ </port>
52
+ </output>
53
+ </layer>
54
+ <layer id="4" name="Convert_290860" type="Convert" version="opset1">
55
+ <data destination_type="f16" />
56
+ <input>
57
+ <port id="0" precision="I8">
58
+ <dim>1280</dim>
59
+ <dim>3</dim>
60
+ <dim>2</dim>
61
+ <dim>14</dim>
62
+ <dim>14</dim>
63
+ </port>
64
+ </input>
65
+ <output>
66
+ <port id="1" precision="FP16">
67
+ <dim>1280</dim>
68
+ <dim>3</dim>
69
+ <dim>2</dim>
70
+ <dim>14</dim>
71
+ <dim>14</dim>
72
+ </port>
73
+ </output>
74
+ </layer>
75
+ <layer id="5" name="self.proj.weight/scale" type="Const" version="opset1">
76
+ <data element_type="f16" shape="1280, 1, 1, 1, 1" offset="1505320" size="2560" />
77
+ <output>
78
+ <port id="0" precision="FP16">
79
+ <dim>1280</dim>
80
+ <dim>1</dim>
81
+ <dim>1</dim>
82
+ <dim>1</dim>
83
+ <dim>1</dim>
84
+ </port>
85
+ </output>
86
+ </layer>
87
+ <layer id="6" name="self.proj.weight/fq_weights_1" type="Multiply" version="opset1">
88
+ <data auto_broadcast="numpy" />
89
+ <input>
90
+ <port id="0" precision="FP16">
91
+ <dim>1280</dim>
92
+ <dim>3</dim>
93
+ <dim>2</dim>
94
+ <dim>14</dim>
95
+ <dim>14</dim>
96
+ </port>
97
+ <port id="1" precision="FP16">
98
+ <dim>1280</dim>
99
+ <dim>1</dim>
100
+ <dim>1</dim>
101
+ <dim>1</dim>
102
+ <dim>1</dim>
103
+ </port>
104
+ </input>
105
+ <output>
106
+ <port id="2" precision="FP16">
107
+ <dim>1280</dim>
108
+ <dim>3</dim>
109
+ <dim>2</dim>
110
+ <dim>14</dim>
111
+ <dim>14</dim>
112
+ </port>
113
+ </output>
114
+ </layer>
115
+ <layer id="7" name="self.proj.weight/fq_weights_1/convert" type="Convert" version="opset1">
116
+ <data destination_type="f32" />
117
+ <input>
118
+ <port id="0" precision="FP16">
119
+ <dim>1280</dim>
120
+ <dim>3</dim>
121
+ <dim>2</dim>
122
+ <dim>14</dim>
123
+ <dim>14</dim>
124
+ </port>
125
+ </input>
126
+ <output>
127
+ <port id="1" precision="FP32">
128
+ <dim>1280</dim>
129
+ <dim>3</dim>
130
+ <dim>2</dim>
131
+ <dim>14</dim>
132
+ <dim>14</dim>
133
+ </port>
134
+ </output>
135
+ </layer>
136
+ <layer id="8" name="__module.proj/aten::_convolution/Convolution" type="Convolution" version="opset1">
137
+ <data strides="2, 14, 14" dilations="1, 1, 1" pads_begin="0, 0, 0" pads_end="0, 0, 0" auto_pad="explicit" />
138
+ <input>
139
+ <port id="0" precision="FP32">
140
+ <dim>-1</dim>
141
+ <dim>3</dim>
142
+ <dim>2</dim>
143
+ <dim>14</dim>
144
+ <dim>14</dim>
145
+ </port>
146
+ <port id="1" precision="FP32">
147
+ <dim>1280</dim>
148
+ <dim>3</dim>
149
+ <dim>2</dim>
150
+ <dim>14</dim>
151
+ <dim>14</dim>
152
+ </port>
153
+ </input>
154
+ <output>
155
+ <port id="2" precision="FP32" names="33">
156
+ <dim>-1</dim>
157
+ <dim>1280</dim>
158
+ <dim>1</dim>
159
+ <dim>1</dim>
160
+ <dim>1</dim>
161
+ </port>
162
+ </output>
163
+ </layer>
164
+ <layer id="9" name="Constant_71234" type="Const" version="opset1">
165
+ <data element_type="i64" shape="2" offset="1507880" size="16" />
166
+ <output>
167
+ <port id="0" precision="I64" names="18">
168
+ <dim>2</dim>
169
+ </port>
170
+ </output>
171
+ </layer>
172
+ <layer id="10" name="aten::view/Reshape_1" type="Reshape" version="opset1">
173
+ <data special_zero="false" />
174
+ <input>
175
+ <port id="0" precision="FP32">
176
+ <dim>-1</dim>
177
+ <dim>1280</dim>
178
+ <dim>1</dim>
179
+ <dim>1</dim>
180
+ <dim>1</dim>
181
+ </port>
182
+ <port id="1" precision="I64">
183
+ <dim>2</dim>
184
+ </port>
185
+ </input>
186
+ <output>
187
+ <port id="2" precision="FP32" names="last_hidden_state">
188
+ <dim>-1</dim>
189
+ <dim>1280</dim>
190
+ </port>
191
+ </output>
192
+ </layer>
193
+ <layer id="11" name="Result_71264" type="Result" version="opset1">
194
+ <input>
195
+ <port id="0" precision="FP32">
196
+ <dim>-1</dim>
197
+ <dim>1280</dim>
198
+ </port>
199
+ </input>
200
+ </layer>
201
+ </layers>
202
+ <edges>
203
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
204
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="1" />
205
+ <edge from-layer="2" from-port="2" to-layer="8" to-port="0" />
206
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="0" />
207
+ <edge from-layer="4" from-port="1" to-layer="6" to-port="0" />
208
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="1" />
209
+ <edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
210
+ <edge from-layer="7" from-port="1" to-layer="8" to-port="1" />
211
+ <edge from-layer="8" from-port="2" to-layer="10" to-port="0" />
212
+ <edge from-layer="9" from-port="0" to-layer="10" to-port="1" />
213
+ <edge from-layer="10" from-port="2" to-layer="11" to-port="0" />
214
+ </edges>
215
+ <rt_info>
216
+ <Runtime_version value="2025.1.0-17990-dc1d9675cbf" />
217
+ <conversion_parameters>
218
+ <framework value="pytorch" />
219
+ <is_python_object value="True" />
220
+ </conversion_parameters>
221
+ <nncf>
222
+ <friendly_names_were_updated value="True" />
223
+ <weight_compression>
224
+ <advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, '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}}" />
225
+ <all_layers value="False" />
226
+ <awq value="False" />
227
+ <backup_mode value="int8_asym" />
228
+ <gptq value="False" />
229
+ <group_size value="-1" />
230
+ <ignored_scope value="[]" />
231
+ <lora_correction value="False" />
232
+ <mode value="int8_sym" />
233
+ <ratio value="1.0" />
234
+ <scale_estimation value="False" />
235
+ <sensitivity_metric value="weight_quantization_error" />
236
+ </weight_compression>
237
+ </nncf>
238
+ <optimum>
239
+ <optimum_intel_version value="1.22.0.dev0+753f84d" />
240
+ <optimum_version value="1.24.0.dev0" />
241
+ <pytorch_version value="2.5.0+cpu" />
242
+ <transformers_version value="4.45.0" />
243
+ </optimum>
244
+ </rt_info>
245
+ </net>
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 12845056,
26
+ "min_pixels": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "model_max_length": 32768,
138
+ "pad_token": "<|endoftext|>",
139
+ "padding_side": "left",
140
+ "processor_class": "Qwen2VLProcessor",
141
+ "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff