Hugging Face's logo

OpenVINO
/
Qwen2.5-VL-7B-Instruct-int4-ov

Image-Text-to-Text
Transformers
OpenVINO
English
qwen2_5_vl
image-to-text
multimodal
conversational
Model card Files
xet
Community
openvino-ci commited on
Commit
788f103
·
verified ·
1 Parent(s): 521d7d3

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. README.md +109 -0
  3. added_tokens.json +24 -0
  4. chat_template.jinja +7 -0
  5. config.json +136 -0
  6. generation_config.json +12 -0
  7. merges.txt +0 -0
  8. openvino_config.json +29 -0
  9. openvino_detokenizer.bin +3 -0
  10. openvino_detokenizer.xml +221 -0
  11. openvino_language_model.bin +3 -0
  12. openvino_language_model.xml +0 -0
  13. openvino_text_embeddings_model.bin +3 -0
  14. openvino_text_embeddings_model.xml +179 -0
  15. openvino_tokenizer.bin +3 -0
  16. openvino_tokenizer.xml +773 -0
  17. openvino_vision_embeddings_merger_model.bin +3 -0
  18. openvino_vision_embeddings_merger_model.xml +0 -0
  19. openvino_vision_embeddings_model.bin +3 -0
  20. openvino_vision_embeddings_model.xml +248 -0
  21. preprocessor_config.json +37 -0
  22. special_tokens_map.json +31 -0
  23. tokenizer.json +3 -0
  24. tokenizer_config.json +208 -0
  25. video_preprocessor_config.json +43 -0
  26. 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
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ pipeline_tag: image-text-to-text
6
+ tags:
7
+ - multimodal
8
+ library_name: transformers
9
+ base_model:
10
+ - Qwen/Qwen2.5-VL-7B-Instruct
11
+ base_model_relation: quantized
12
+ ---
13
+
14
+ # Qwen2.5-VL-7B-Instruct-int4-ov
15
+
16
+ * Model creator: [Qwen](https://huggingface.co/Qwen)
17
+ * Original model: [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)
18
+
19
+ ## Description
20
+
21
+ This is [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2025/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to INT4 by [NNCF](https://github.com/openvinotoolkit/nncf).
22
+
23
+
24
+ ## Quantization Parameters
25
+
26
+ Weight compression was performed using `nncf.compress_weights` with the following parameters:
27
+
28
+ * mode: **INT4_ASYM**
29
+
30
+ ## Compatibility
31
+
32
+ The provided OpenVINO™ IR model is compatible with:
33
+
34
+ * OpenVINO version 2025.4.0 and higher
35
+ * Optimum Intel 1.27.0 and higher
36
+
37
+
38
+ ## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
39
+
40
+ 1. Install packages required for using OpenVINO GenAI.
41
+ ```
42
+ pip install --pre -U --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release openvino openvino-tokenizers openvino-genai
43
+
44
+ pip install huggingface_hub
45
+ ```
46
+
47
+ 2. Download model from HuggingFace Hub
48
+
49
+ ```
50
+ import huggingface_hub as hf_hub
51
+
52
+ model_id = "OpenVINO/Qwen2.5-VL-7B-Instruct-int4-ov"
53
+ model_path = "Qwen2.5-VL-7B-Instruct-int4-ov"
54
+
55
+ hf_hub.snapshot_download(model_id, local_dir=model_path)
56
+
57
+ ```
58
+
59
+ 1. Run model inference:
60
+
61
+ ```
62
+ import openvino_genai as ov_genai
63
+ import requests
64
+ from PIL import Image
65
+ from io import BytesIO
66
+ import numpy as np
67
+ import openvino as ov
68
+
69
+ device = "CPU"
70
+ pipe = ov_genai.VLMPipeline(model_path, device)
71
+
72
+ def load_image(image_file):
73
+ if isinstance(image_file, str) and (image_file.startswith("http") or image_file.startswith("https")):
74
+ response = requests.get(image_file)
75
+ image = Image.open(BytesIO(response.content)).convert("RGB")
76
+ else:
77
+ image = Image.open(image_file).convert("RGB")
78
+ image_data = np.array(image.getdata()).reshape(1, image.size[1], image.size[0], 3).astype(np.byte)
79
+ return ov.Tensor(image_data)
80
+
81
+ prompt = "What is unusual in this picture?"
82
+
83
+ url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
84
+ image_tensor = load_image(url)
85
+
86
+ def streamer(subword: str) -> bool:
87
+ print(subword, end="", flush=True)
88
+ return False
89
+
90
+ pipe.start_chat()
91
+ output = pipe.generate(prompt, image=image_tensor, max_new_tokens=100, streamer=streamer)
92
+ pipe.finish_chat()
93
+ ```
94
+
95
+ More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
96
+
97
+
98
+ ## Limitations
99
+
100
+ Check the original [model card](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) for limitations.
101
+
102
+ ## Legal information
103
+
104
+ The original model is distributed under [apache-2.0](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md) license. More details can be found in [original model card](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
105
+
106
+ ## Disclaimer
107
+
108
+ Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.
109
+
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
33
+ "architectures": [
34
+ "Qwen2_5_VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention"
73
+ ],
74
+ "max_position_embeddings": 128000,
75
+ "max_window_layers": 28,
76
+ "model_type": "qwen2_5_vl_text",
77
+ "num_attention_heads": 28,
78
+ "num_hidden_layers": 28,
79
+ "num_key_value_heads": 4,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_scaling": {
82
+ "mrope_section": [
83
+ 16,
84
+ 24,
85
+ 24
86
+ ],
87
+ "rope_type": "default",
88
+ "type": "default"
89
+ },
90
+ "rope_theta": 1000000.0,
91
+ "sliding_window": null,
92
+ "torch_dtype": "bfloat16",
93
+ "use_cache": true,
94
+ "use_sliding_window": false,
95
+ "video_token_id": null,
96
+ "vision_end_token_id": 151653,
97
+ "vision_start_token_id": 151652,
98
+ "vision_token_id": 151654,
99
+ "vocab_size": 152064
100
+ },
101
+ "tie_word_embeddings": false,
102
+ "torch_dtype": "bfloat16",
103
+ "transformers_version": "4.55.4",
104
+ "use_cache": true,
105
+ "use_sliding_window": false,
106
+ "video_token_id": 151656,
107
+ "vision_config": {
108
+ "depth": 32,
109
+ "fullatt_block_indexes": [
110
+ 7,
111
+ 15,
112
+ 23,
113
+ 31
114
+ ],
115
+ "hidden_act": "silu",
116
+ "hidden_size": 1280,
117
+ "in_channels": 3,
118
+ "in_chans": 3,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 3420,
121
+ "model_type": "qwen2_5_vl",
122
+ "num_heads": 16,
123
+ "out_hidden_size": 3584,
124
+ "patch_size": 14,
125
+ "spatial_merge_size": 2,
126
+ "spatial_patch_size": 14,
127
+ "temporal_patch_size": 2,
128
+ "tokens_per_second": 2,
129
+ "torch_dtype": "bfloat16",
130
+ "window_size": 112
131
+ },
132
+ "vision_end_token_id": 151653,
133
+ "vision_start_token_id": 151652,
134
+ "vision_token_id": 151654,
135
+ "vocab_size": 152064
136
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.55.4"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dtype": "int4",
3
+ "input_info": null,
4
+ "optimum_version": "2.0.0",
5
+ "output_attentions": false,
6
+ "quantization_config": {
7
+ "all_layers": null,
8
+ "backup_precision": null,
9
+ "bits": 4,
10
+ "dataset": null,
11
+ "dtype": "int4",
12
+ "gptq": null,
13
+ "group_size": 128,
14
+ "ignored_scope": null,
15
+ "lora_correction": null,
16
+ "num_samples": null,
17
+ "processor": null,
18
+ "quant_method": "default",
19
+ "ratio": 1.0,
20
+ "scale_estimation": null,
21
+ "sensitivity_metric": null,
22
+ "statistics_path": null,
23
+ "sym": false,
24
+ "tokenizer": null,
25
+ "trust_remote_code": true
26
+ },
27
+ "save_onnx_model": false,
28
+ "transformers_version": "4.55.4"
29
+ }
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ca47601554a3b871c1e45e8f31aa6e17d726365c075fb430d1a2089484ae8d6
3
+ size 2189639
openvino_detokenizer.xml ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_1947893" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_1947893">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_1948092" 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_1947895" type="Const" version="opset1">
29
+ <data element_type="i32" shape="151665" offset="0" size="606660" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>151665</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_1947897" type="Const" version="opset1">
37
+ <data element_type="i32" shape="151665" offset="606660" size="606660" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>151665</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_1947899" type="Const" version="opset1">
45
+ <data element_type="u8" shape="976263" offset="1213320" size="976263" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>976263</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Slice_1947904" type="Const" version="opset1">
53
+ <data element_type="i32" shape="14" offset="2189583" size="56" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>14</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="VocabDecoder_1947906" 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>151665</dim>
69
+ </port>
70
+ <port id="2" precision="I32">
71
+ <dim>151665</dim>
72
+ </port>
73
+ <port id="3" precision="U8">
74
+ <dim>976263</dim>
75
+ </port>
76
+ <port id="4" precision="I32">
77
+ <dim>14</dim>
78
+ </port>
79
+ </input>
80
+ <output>
81
+ <port id="5" precision="I32">
82
+ <dim>-1</dim>
83
+ </port>
84
+ <port id="6" precision="I32">
85
+ <dim>-1</dim>
86
+ </port>
87
+ <port id="7" precision="I32">
88
+ <dim>-1</dim>
89
+ </port>
90
+ <port id="8" precision="I32">
91
+ <dim>-1</dim>
92
+ </port>
93
+ <port id="9" precision="U8">
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="FuzeRagged_1947907" type="FuzeRagged" version="extension">
99
+ <input>
100
+ <port id="0" precision="I32">
101
+ <dim>-1</dim>
102
+ </port>
103
+ <port id="1" precision="I32">
104
+ <dim>-1</dim>
105
+ </port>
106
+ <port id="2" precision="I32">
107
+ <dim>-1</dim>
108
+ </port>
109
+ <port id="3" precision="I32">
110
+ <dim>-1</dim>
111
+ </port>
112
+ </input>
113
+ <output>
114
+ <port id="4" precision="I32">
115
+ <dim>-1</dim>
116
+ </port>
117
+ <port id="5" precision="I32">
118
+ <dim>-1</dim>
119
+ </port>
120
+ </output>
121
+ </layer>
122
+ <layer id="8" name="UTF8Validate_1947908" type="UTF8Validate" version="extension">
123
+ <data replace_mode="true" />
124
+ <input>
125
+ <port id="0" precision="I32">
126
+ <dim>-1</dim>
127
+ </port>
128
+ <port id="1" precision="I32">
129
+ <dim>-1</dim>
130
+ </port>
131
+ <port id="2" precision="U8">
132
+ <dim>-1</dim>
133
+ </port>
134
+ </input>
135
+ <output>
136
+ <port id="3" precision="I32">
137
+ <dim>-1</dim>
138
+ </port>
139
+ <port id="4" precision="I32">
140
+ <dim>-1</dim>
141
+ </port>
142
+ <port id="5" precision="U8">
143
+ <dim>-1</dim>
144
+ </port>
145
+ </output>
146
+ </layer>
147
+ <layer id="9" name="StringTensorPack_1947909" type="StringTensorPack" version="opset15">
148
+ <input>
149
+ <port id="0" precision="I32">
150
+ <dim>-1</dim>
151
+ </port>
152
+ <port id="1" precision="I32">
153
+ <dim>-1</dim>
154
+ </port>
155
+ <port id="2" precision="U8">
156
+ <dim>-1</dim>
157
+ </port>
158
+ </input>
159
+ <output>
160
+ <port id="3" precision="STRING" names="Result_1947910,string_output">
161
+ <dim>-1</dim>
162
+ </port>
163
+ </output>
164
+ </layer>
165
+ <layer id="10" name="Result_1947910" type="Result" version="opset1" output_names="Result_1947910,string_output">
166
+ <input>
167
+ <port id="0" precision="STRING">
168
+ <dim>-1</dim>
169
+ </port>
170
+ </input>
171
+ </layer>
172
+ </layers>
173
+ <edges>
174
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
175
+ <edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
176
+ <edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
177
+ <edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
178
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
179
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
180
+ <edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
181
+ <edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
182
+ <edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
183
+ <edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
184
+ <edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
185
+ <edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
186
+ <edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
187
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
188
+ <edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
189
+ <edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
190
+ <edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
191
+ </edges>
192
+ <rt_info>
193
+ <add_attention_mask value="True" />
194
+ <add_prefix_space />
195
+ <add_special_tokens value="True" />
196
+ <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 %}" />
197
+ <clean_up_tokenization_spaces />
198
+ <detokenizer_input_type value="i64" />
199
+ <eos_token_id value="151645" />
200
+ <handle_special_tokens_with_re />
201
+ <max_length />
202
+ <number_of_inputs value="1" />
203
+ <openvino_tokenizers_version value="2025.4.0.0-625-3694f87878e" />
204
+ <openvino_version value="2025.4.0-20398-7a975177ff4-releases/2025/4" />
205
+ <original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
206
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
207
+ <pad_token_id value="151643" />
208
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 0]}}" />
209
+ <sentencepiece_version value="0.2.1" />
210
+ <skip_special_tokens value="True" />
211
+ <streaming_detokenizer value="False" />
212
+ <tiktoken_version value="0.12.0" />
213
+ <tokenizer_output_type value="i64" />
214
+ <tokenizers_version value="0.21.4" />
215
+ <transformers_version value="4.55.4" />
216
+ <use_max_padding value="False" />
217
+ <use_sentencepiece_backend value="False" />
218
+ <utf8_replace_mode value="replace" />
219
+ <with_detokenizer value="True" />
220
+ </rt_info>
221
+ </net>
openvino_language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706a250a772076720509612c3dd3bf4a153a9ceb5d03167ca482f397a2dbdd17
3
+ size 3936620681
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 sha256:2587d484d643ce5a8a914af9d539c8485f5c1ee13b6c062692b15aa1e6dd27b5
3
+ size 545301508
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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="152064, 3584" offset="0" size="544997376" />
15
+ <output>
16
+ <port id="0" precision="I8">
17
+ <dim>152064</dim>
18
+ <dim>3584</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="Convert_1163571" type="Convert" version="opset1">
23
+ <data destination_type="f16" />
24
+ <input>
25
+ <port id="0" precision="I8">
26
+ <dim>152064</dim>
27
+ <dim>3584</dim>
28
+ </port>
29
+ </input>
30
+ <output>
31
+ <port id="1" precision="FP16">
32
+ <dim>152064</dim>
33
+ <dim>3584</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="152064, 1" offset="544997376" size="304128" />
39
+ <output>
40
+ <port id="0" precision="FP16">
41
+ <dim>152064</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>152064</dim>
51
+ <dim>3584</dim>
52
+ </port>
53
+ <port id="1" precision="FP16">
54
+ <dim>152064</dim>
55
+ <dim>1</dim>
56
+ </port>
57
+ </input>
58
+ <output>
59
+ <port id="2" precision="FP16">
60
+ <dim>152064</dim>
61
+ <dim>3584</dim>
62
+ </port>
63
+ </output>
64
+ </layer>
65
+ <layer id="5" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
66
+ <data destination_type="f32" />
67
+ <rt_info>
68
+ <attribute name="decompression" version="0" />
69
+ </rt_info>
70
+ <input>
71
+ <port id="0" precision="FP16">
72
+ <dim>152064</dim>
73
+ <dim>3584</dim>
74
+ </port>
75
+ </input>
76
+ <output>
77
+ <port id="1" precision="FP32">
78
+ <dim>152064</dim>
79
+ <dim>3584</dim>
80
+ </port>
81
+ </output>
82
+ </layer>
83
+ <layer id="6" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
84
+ <data destination_type="i32" />
85
+ <input>
86
+ <port id="0" precision="I64">
87
+ <dim>-1</dim>
88
+ <dim>-1</dim>
89
+ </port>
90
+ </input>
91
+ <output>
92
+ <port id="1" precision="I32">
93
+ <dim>-1</dim>
94
+ <dim>-1</dim>
95
+ </port>
96
+ </output>
97
+ </layer>
98
+ <layer id="7" name="ov_ext::embedding/Constant" type="Const" version="opset1">
99
+ <data element_type="i32" shape="" offset="545301504" size="4" />
100
+ <output>
101
+ <port id="0" precision="I32" />
102
+ </output>
103
+ </layer>
104
+ <layer id="8" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
105
+ <data batch_dims="0" />
106
+ <input>
107
+ <port id="0" precision="FP32">
108
+ <dim>152064</dim>
109
+ <dim>3584</dim>
110
+ </port>
111
+ <port id="1" precision="I32">
112
+ <dim>-1</dim>
113
+ <dim>-1</dim>
114
+ </port>
115
+ <port id="2" precision="I32" />
116
+ </input>
117
+ <output>
118
+ <port id="3" precision="FP32" names="inputs_embeds">
119
+ <dim>-1</dim>
120
+ <dim>-1</dim>
121
+ <dim>3584</dim>
122
+ </port>
123
+ </output>
124
+ </layer>
125
+ <layer id="9" name="Result_180027" type="Result" version="opset1" output_names="inputs_embeds">
126
+ <input>
127
+ <port id="0" precision="FP32">
128
+ <dim>-1</dim>
129
+ <dim>-1</dim>
130
+ <dim>3584</dim>
131
+ </port>
132
+ </input>
133
+ </layer>
134
+ </layers>
135
+ <edges>
136
+ <edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
137
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
138
+ <edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
139
+ <edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
140
+ <edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
141
+ <edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
142
+ <edge from-layer="6" from-port="1" to-layer="8" to-port="1" />
143
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
144
+ <edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
145
+ </edges>
146
+ <rt_info>
147
+ <Runtime_version value="2025.4.0-20398-7a975177ff4-releases/2025/4" />
148
+ <conversion_parameters>
149
+ <framework value="pytorch" />
150
+ <is_python_object value="True" />
151
+ </conversion_parameters>
152
+ <nncf>
153
+ <friendly_names_were_updated value="True" />
154
+ <version value="2.19.0" />
155
+ <weight_compression>
156
+ <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}" />
157
+ <all_layers value="False" />
158
+ <awq value="False" />
159
+ <backup_mode value="int8_asym" />
160
+ <compression_format value="dequantize" />
161
+ <gptq value="False" />
162
+ <group_size value="-1" />
163
+ <ignored_scope value="[]" />
164
+ <lora_correction value="False" />
165
+ <mode value="int8_sym" />
166
+ <ratio value="1.0" />
167
+ <scale_estimation value="False" />
168
+ <sensitivity_metric value="weight_quantization_error" />
169
+ </weight_compression>
170
+ </nncf>
171
+ <optimum>
172
+ <nncf_version value="2.19.0.dev0+473ef3228" />
173
+ <optimum_intel_version value="1.27.0.dev0+906008d" />
174
+ <optimum_version value="2.0.0" />
175
+ <pytorch_version value="2.9.1+cpu" />
176
+ <transformers_version value="4.55.4" />
177
+ </optimum>
178
+ </rt_info>
179
+ </net>
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651d8b86c94c40710919f6089189a748ebf4ad1b0f0da728440454d14379b078
3
+ size 5588603
openvino_tokenizer.xml ADDED
@@ -0,0 +1,773 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_1947765" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_1947765">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_1947771" 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_1947766" type="StringTensorUnpack" version="opset15">
19
+ <input>
20
+ <port id="0" precision="STRING">
21
+ <dim>-1</dim>
22
+ </port>
23
+ </input>
24
+ <output>
25
+ <port id="1" precision="I32">
26
+ <dim>-1</dim>
27
+ </port>
28
+ <port id="2" precision="I32">
29
+ <dim>-1</dim>
30
+ </port>
31
+ <port id="3" precision="U8">
32
+ <dim>-1</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="ShapeOf_1947767" type="ShapeOf" version="opset3">
37
+ <data output_type="i64" />
38
+ <input>
39
+ <port id="0" precision="I32">
40
+ <dim>-1</dim>
41
+ </port>
42
+ </input>
43
+ <output>
44
+ <port id="1" precision="I64">
45
+ <dim>1</dim>
46
+ </port>
47
+ </output>
48
+ </layer>
49
+ <layer id="4" name="Constant_1947768" type="Const" version="opset1">
50
+ <data element_type="i64" shape="" offset="0" size="8" />
51
+ <output>
52
+ <port id="0" precision="I64" />
53
+ </output>
54
+ </layer>
55
+ <layer id="5" name="Constant_1947769" type="Const" version="opset1">
56
+ <data element_type="i64" shape="" offset="0" size="8" />
57
+ <output>
58
+ <port id="0" precision="I64" />
59
+ </output>
60
+ </layer>
61
+ <layer id="6" name="Gather_1947770" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="I64">
65
+ <dim>1</dim>
66
+ </port>
67
+ <port id="1" precision="I64" />
68
+ <port id="2" precision="I64" />
69
+ </input>
70
+ <output>
71
+ <port id="3" precision="I64" />
72
+ </output>
73
+ </layer>
74
+ <layer id="7" name="Constant_1947772" type="Const" version="opset1">
75
+ <data element_type="i64" shape="" offset="8" size="8" />
76
+ <output>
77
+ <port id="0" precision="I64" />
78
+ </output>
79
+ </layer>
80
+ <layer id="8" name="Range_1947773" type="Range" version="opset4">
81
+ <data output_type="i32" />
82
+ <input>
83
+ <port id="0" precision="I64" />
84
+ <port id="1" precision="I64" />
85
+ <port id="2" precision="I64" />
86
+ </input>
87
+ <output>
88
+ <port id="3" precision="I32">
89
+ <dim>-1</dim>
90
+ </port>
91
+ </output>
92
+ </layer>
93
+ <layer id="9" name="Constant_1947774" type="Const" version="opset1">
94
+ <data element_type="i64" shape="" offset="8" size="8" />
95
+ <output>
96
+ <port id="0" precision="I64" />
97
+ </output>
98
+ </layer>
99
+ <layer id="10" name="Constant_1947775" type="Const" version="opset1">
100
+ <data element_type="i64" shape="" offset="8" size="8" />
101
+ <output>
102
+ <port id="0" precision="I64" />
103
+ </output>
104
+ </layer>
105
+ <layer id="11" name="Add_1947776" type="Add" version="opset1">
106
+ <data auto_broadcast="numpy" />
107
+ <input>
108
+ <port id="0" precision="I64" />
109
+ <port id="1" precision="I64" />
110
+ </input>
111
+ <output>
112
+ <port id="2" precision="I64" />
113
+ </output>
114
+ </layer>
115
+ <layer id="12" name="Constant_1947777" type="Const" version="opset1">
116
+ <data element_type="i64" shape="" offset="8" size="8" />
117
+ <output>
118
+ <port id="0" precision="I64" />
119
+ </output>
120
+ </layer>
121
+ <layer id="13" name="Range_1947778" type="Range" version="opset4">
122
+ <data output_type="i32" />
123
+ <input>
124
+ <port id="0" precision="I64" />
125
+ <port id="1" precision="I64" />
126
+ <port id="2" precision="I64" />
127
+ </input>
128
+ <output>
129
+ <port id="3" precision="I32">
130
+ <dim>-1</dim>
131
+ </port>
132
+ </output>
133
+ </layer>
134
+ <layer id="14" name="Constant_1947842" type="Const" version="opset1">
135
+ <data element_type="u8" shape="402" offset="16" size="402" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>402</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_1947843" type="SpecialTokensSplit" version="extension">
143
+ <input>
144
+ <port id="0" precision="I32">
145
+ <dim>-1</dim>
146
+ </port>
147
+ <port id="1" precision="I32">
148
+ <dim>-1</dim>
149
+ </port>
150
+ <port id="2" precision="I32">
151
+ <dim>-1</dim>
152
+ </port>
153
+ <port id="3" precision="I32">
154
+ <dim>-1</dim>
155
+ </port>
156
+ <port id="4" precision="U8">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="5" precision="U8">
160
+ <dim>402</dim>
161
+ </port>
162
+ </input>
163
+ <output>
164
+ <port id="6" precision="I32">
165
+ <dim>-1</dim>
166
+ </port>
167
+ <port id="7" precision="I32">
168
+ <dim>-1</dim>
169
+ </port>
170
+ <port id="8" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="9" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ <port id="10" precision="U8">
177
+ <dim>-1</dim>
178
+ </port>
179
+ <port id="11" precision="BOOL">
180
+ <dim>-1</dim>
181
+ </port>
182
+ </output>
183
+ </layer>
184
+ <layer id="16" name="CharsMapNormalization_1947844" type="CharsMapNormalization" version="extension">
185
+ <data add_dummy_prefix="false" remove_extra_whitespaces="false" escape_whitespaces="false" normalization_form="nfc" case_fold="false" nmt="false" />
186
+ <input>
187
+ <port id="0" precision="I32">
188
+ <dim>-1</dim>
189
+ </port>
190
+ <port id="1" precision="I32">
191
+ <dim>-1</dim>
192
+ </port>
193
+ <port id="2" precision="U8">
194
+ <dim>-1</dim>
195
+ </port>
196
+ <port id="3" precision="BOOL">
197
+ <dim>-1</dim>
198
+ </port>
199
+ </input>
200
+ <output>
201
+ <port id="4" precision="I32">
202
+ <dim>-1</dim>
203
+ </port>
204
+ <port id="5" precision="I32">
205
+ <dim>-1</dim>
206
+ </port>
207
+ <port id="6" precision="U8">
208
+ <dim>-1</dim>
209
+ </port>
210
+ <port id="7" precision="BOOL">
211
+ <dim>-1</dim>
212
+ </port>
213
+ </output>
214
+ </layer>
215
+ <layer id="17" name="Constant_1947846" type="Const" version="opset1">
216
+ <data element_type="u8" shape="110" offset="418" size="110" />
217
+ <output>
218
+ <port id="0" precision="U8">
219
+ <dim>110</dim>
220
+ </port>
221
+ </output>
222
+ </layer>
223
+ <layer id="18" name="RegexSplit_1947847" type="RegexSplit" version="extension">
224
+ <data behaviour="isolate" invert="false" max_splits="-1" />
225
+ <input>
226
+ <port id="0" precision="I32">
227
+ <dim>-1</dim>
228
+ </port>
229
+ <port id="1" precision="I32">
230
+ <dim>-1</dim>
231
+ </port>
232
+ <port id="2" precision="I32">
233
+ <dim>-1</dim>
234
+ </port>
235
+ <port id="3" precision="I32">
236
+ <dim>-1</dim>
237
+ </port>
238
+ <port id="4" precision="U8">
239
+ <dim>-1</dim>
240
+ </port>
241
+ <port id="5" precision="BOOL">
242
+ <dim>-1</dim>
243
+ </port>
244
+ <port id="6" precision="U8">
245
+ <dim>110</dim>
246
+ </port>
247
+ </input>
248
+ <output>
249
+ <port id="7" precision="I32">
250
+ <dim>-1</dim>
251
+ </port>
252
+ <port id="8" precision="I32">
253
+ <dim>-1</dim>
254
+ </port>
255
+ <port id="9" precision="I32">
256
+ <dim>-1</dim>
257
+ </port>
258
+ <port id="10" precision="I32">
259
+ <dim>-1</dim>
260
+ </port>
261
+ <port id="11" precision="U8">
262
+ <dim>-1</dim>
263
+ </port>
264
+ <port id="12" precision="BOOL">
265
+ <dim>-1</dim>
266
+ </port>
267
+ </output>
268
+ </layer>
269
+ <layer id="19" name="Constant_1947849" type="Const" version="opset1">
270
+ <data element_type="i32" shape="151665" offset="528" size="606660" />
271
+ <output>
272
+ <port id="0" precision="I32">
273
+ <dim>151665</dim>
274
+ </port>
275
+ </output>
276
+ </layer>
277
+ <layer id="20" name="Constant_1947851" type="Const" version="opset1">
278
+ <data element_type="i32" shape="151665" offset="607188" size="606660" />
279
+ <output>
280
+ <port id="0" precision="I32">
281
+ <dim>151665</dim>
282
+ </port>
283
+ </output>
284
+ </layer>
285
+ <layer id="21" name="Constant_1947853" type="Const" version="opset1">
286
+ <data element_type="u8" shape="976263" offset="1213848" size="976263" />
287
+ <output>
288
+ <port id="0" precision="U8">
289
+ <dim>976263</dim>
290
+ </port>
291
+ </output>
292
+ </layer>
293
+ <layer id="22" name="Constant_1947861" type="Const" version="opset1">
294
+ <data element_type="i32" shape="151387" offset="2190111" size="605548" />
295
+ <output>
296
+ <port id="0" precision="I32">
297
+ <dim>151387</dim>
298
+ </port>
299
+ </output>
300
+ </layer>
301
+ <layer id="23" name="Constant_1947863" type="Const" version="opset1">
302
+ <data element_type="i32" shape="151387" offset="2795659" size="605548" />
303
+ <output>
304
+ <port id="0" precision="I32">
305
+ <dim>151387</dim>
306
+ </port>
307
+ </output>
308
+ </layer>
309
+ <layer id="24" name="Constant_1947865" type="Const" version="opset1">
310
+ <data element_type="u8" shape="491359" offset="3401207" size="491359" />
311
+ <output>
312
+ <port id="0" precision="U8">
313
+ <dim>491359</dim>
314
+ </port>
315
+ </output>
316
+ </layer>
317
+ <layer id="25" name="Constant_1947867" type="Const" version="opset1">
318
+ <data element_type="i32" shape="151387" offset="3892566" size="605548" />
319
+ <output>
320
+ <port id="0" precision="I32">
321
+ <dim>151387</dim>
322
+ </port>
323
+ </output>
324
+ </layer>
325
+ <layer id="26" name="Constant_1947869" type="Const" version="opset1">
326
+ <data element_type="i32" shape="151387" offset="4498114" size="605548" />
327
+ <output>
328
+ <port id="0" precision="I32">
329
+ <dim>151387</dim>
330
+ </port>
331
+ </output>
332
+ </layer>
333
+ <layer id="27" name="Constant_1947871" type="Const" version="opset1">
334
+ <data element_type="u8" shape="484354" offset="5103662" size="484354" />
335
+ <output>
336
+ <port id="0" precision="U8">
337
+ <dim>484354</dim>
338
+ </port>
339
+ </output>
340
+ </layer>
341
+ <layer id="28" name="Constant_1947855" type="Const" version="opset1">
342
+ <data element_type="i32" shape="22" offset="5588016" size="88" />
343
+ <output>
344
+ <port id="0" precision="I32">
345
+ <dim>22</dim>
346
+ </port>
347
+ </output>
348
+ </layer>
349
+ <layer id="29" name="Constant_1947857" type="Const" version="opset1">
350
+ <data element_type="i32" shape="22" offset="5588104" size="88" />
351
+ <output>
352
+ <port id="0" precision="I32">
353
+ <dim>22</dim>
354
+ </port>
355
+ </output>
356
+ </layer>
357
+ <layer id="30" name="Constant_1947859" type="Const" version="opset1">
358
+ <data element_type="u8" shape="294" offset="5588192" size="294" />
359
+ <output>
360
+ <port id="0" precision="U8">
361
+ <dim>294</dim>
362
+ </port>
363
+ </output>
364
+ </layer>
365
+ <layer id="31" name="Constant_1947872" type="Const" version="opset1">
366
+ <data element_type="i32" shape="22" offset="5588486" size="88" />
367
+ <output>
368
+ <port id="0" precision="I32">
369
+ <dim>22</dim>
370
+ </port>
371
+ </output>
372
+ </layer>
373
+ <layer id="32" name="BPETokenizer_1947873" type="BPETokenizer" version="extension">
374
+ <data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
375
+ <input>
376
+ <port id="0" precision="I32">
377
+ <dim>-1</dim>
378
+ </port>
379
+ <port id="1" precision="I32">
380
+ <dim>-1</dim>
381
+ </port>
382
+ <port id="2" precision="I32">
383
+ <dim>-1</dim>
384
+ </port>
385
+ <port id="3" precision="I32">
386
+ <dim>-1</dim>
387
+ </port>
388
+ <port id="4" precision="U8">
389
+ <dim>-1</dim>
390
+ </port>
391
+ <port id="5" precision="I32">
392
+ <dim>151665</dim>
393
+ </port>
394
+ <port id="6" precision="I32">
395
+ <dim>151665</dim>
396
+ </port>
397
+ <port id="7" precision="U8">
398
+ <dim>976263</dim>
399
+ </port>
400
+ <port id="8" precision="I32">
401
+ <dim>151387</dim>
402
+ </port>
403
+ <port id="9" precision="I32">
404
+ <dim>151387</dim>
405
+ </port>
406
+ <port id="10" precision="U8">
407
+ <dim>491359</dim>
408
+ </port>
409
+ <port id="11" precision="I32">
410
+ <dim>151387</dim>
411
+ </port>
412
+ <port id="12" precision="I32">
413
+ <dim>151387</dim>
414
+ </port>
415
+ <port id="13" precision="U8">
416
+ <dim>484354</dim>
417
+ </port>
418
+ <port id="14" precision="I32">
419
+ <dim>22</dim>
420
+ </port>
421
+ <port id="15" precision="I32">
422
+ <dim>22</dim>
423
+ </port>
424
+ <port id="16" precision="U8">
425
+ <dim>294</dim>
426
+ </port>
427
+ <port id="17" precision="I32">
428
+ <dim>22</dim>
429
+ </port>
430
+ </input>
431
+ <output>
432
+ <port id="18" precision="I32">
433
+ <dim>-1</dim>
434
+ </port>
435
+ <port id="19" precision="I32">
436
+ <dim>-1</dim>
437
+ </port>
438
+ <port id="20" precision="I32">
439
+ <dim>-1</dim>
440
+ </port>
441
+ </output>
442
+ </layer>
443
+ <layer id="33" name="Constant_1947874" type="Const" version="opset1">
444
+ <data element_type="i32" shape="" offset="5588574" size="4" />
445
+ <output>
446
+ <port id="0" precision="I32" />
447
+ </output>
448
+ </layer>
449
+ <layer id="34" name="Constant_1947876" type="Const" version="opset1">
450
+ <data element_type="u8" shape="4" offset="5588578" size="4" />
451
+ <output>
452
+ <port id="0" precision="U8">
453
+ <dim>4</dim>
454
+ </port>
455
+ </output>
456
+ </layer>
457
+ <layer id="35" name="Constant_1947878" type="Const" version="opset1">
458
+ <data element_type="u8" shape="13" offset="5588582" size="13" />
459
+ <output>
460
+ <port id="0" precision="U8">
461
+ <dim>13</dim>
462
+ </port>
463
+ </output>
464
+ </layer>
465
+ <layer id="36" name="Truncate_1947879" type="Truncate" version="extension">
466
+ <data m_num_inputs="1" />
467
+ <input>
468
+ <port id="0" precision="I32">
469
+ <dim>-1</dim>
470
+ </port>
471
+ <port id="1" precision="I32">
472
+ <dim>-1</dim>
473
+ </port>
474
+ <port id="2" precision="I32">
475
+ <dim>-1</dim>
476
+ </port>
477
+ <port id="3" precision="I32" />
478
+ <port id="4" precision="U8">
479
+ <dim>4</dim>
480
+ </port>
481
+ <port id="5" precision="U8">
482
+ <dim>13</dim>
483
+ </port>
484
+ </input>
485
+ <output>
486
+ <port id="6" precision="I32">
487
+ <dim>-1</dim>
488
+ </port>
489
+ <port id="7" precision="I32">
490
+ <dim>-1</dim>
491
+ </port>
492
+ <port id="8" precision="I32">
493
+ <dim>-1</dim>
494
+ </port>
495
+ </output>
496
+ </layer>
497
+ <layer id="37" name="Constant_1947880" type="Const" version="opset1">
498
+ <data element_type="i32" shape="1" offset="5588595" size="4" />
499
+ <output>
500
+ <port id="0" precision="I32">
501
+ <dim>1</dim>
502
+ </port>
503
+ </output>
504
+ </layer>
505
+ <layer id="38" name="CombineSegments_1947881" type="CombineSegments" version="extension">
506
+ <input>
507
+ <port id="0" precision="I32">
508
+ <dim>-1</dim>
509
+ </port>
510
+ <port id="1" precision="I32">
511
+ <dim>-1</dim>
512
+ </port>
513
+ <port id="2" precision="I32">
514
+ <dim>-1</dim>
515
+ </port>
516
+ <port id="3" precision="I32">
517
+ <dim>1</dim>
518
+ </port>
519
+ </input>
520
+ <output>
521
+ <port id="4" precision="I32">
522
+ <dim>-1</dim>
523
+ </port>
524
+ <port id="5" precision="I32">
525
+ <dim>-1</dim>
526
+ </port>
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
+ <port id="9" precision="I32">
537
+ <dim>-1</dim>
538
+ </port>
539
+ </output>
540
+ </layer>
541
+ <layer id="39" name="Subtract_1947882" type="Subtract" version="opset1">
542
+ <data auto_broadcast="numpy" />
543
+ <input>
544
+ <port id="0" precision="I32">
545
+ <dim>-1</dim>
546
+ </port>
547
+ <port id="1" precision="I32">
548
+ <dim>-1</dim>
549
+ </port>
550
+ </input>
551
+ <output>
552
+ <port id="2" precision="I32">
553
+ <dim>-1</dim>
554
+ </port>
555
+ </output>
556
+ </layer>
557
+ <layer id="40" name="Constant_1947883" type="Const" version="opset1">
558
+ <data element_type="i32" shape="" offset="5588595" size="4" />
559
+ <output>
560
+ <port id="0" precision="I32" />
561
+ </output>
562
+ </layer>
563
+ <layer id="41" name="ReduceMax_1947884" type="ReduceMax" version="opset1">
564
+ <data keep_dims="false" />
565
+ <input>
566
+ <port id="0" precision="I32">
567
+ <dim>-1</dim>
568
+ </port>
569
+ <port id="1" precision="I32" />
570
+ </input>
571
+ <output>
572
+ <port id="2" precision="I32" />
573
+ </output>
574
+ </layer>
575
+ <layer id="42" name="Constant_1947885" type="Const" version="opset1">
576
+ <data element_type="i32" shape="" offset="5588599" size="4" />
577
+ <output>
578
+ <port id="0" precision="I32" />
579
+ </output>
580
+ </layer>
581
+ <layer id="43" name="RaggedToDense_1947886" type="RaggedToDense" version="extension">
582
+ <data pad_right="false" m_pad_max_length="false" />
583
+ <input>
584
+ <port id="0" precision="I32">
585
+ <dim>-1</dim>
586
+ </port>
587
+ <port id="1" precision="I32">
588
+ <dim>-1</dim>
589
+ </port>
590
+ <port id="2" precision="I32">
591
+ <dim>-1</dim>
592
+ </port>
593
+ <port id="3" precision="I32" />
594
+ <port id="4" precision="I32" />
595
+ </input>
596
+ <output>
597
+ <port id="5" precision="I32">
598
+ <dim>-1</dim>
599
+ <dim>-1</dim>
600
+ </port>
601
+ <port id="6" precision="BOOL">
602
+ <dim>-1</dim>
603
+ <dim>-1</dim>
604
+ </port>
605
+ </output>
606
+ </layer>
607
+ <layer id="44" name="Convert_1947887" type="Convert" version="opset1">
608
+ <data destination_type="i32" />
609
+ <input>
610
+ <port id="0" precision="BOOL">
611
+ <dim>-1</dim>
612
+ <dim>-1</dim>
613
+ </port>
614
+ </input>
615
+ <output>
616
+ <port id="1" precision="I32">
617
+ <dim>-1</dim>
618
+ <dim>-1</dim>
619
+ </port>
620
+ </output>
621
+ </layer>
622
+ <layer id="45" name="Convert_1947887.0" type="Convert" version="opset1">
623
+ <data destination_type="i64" />
624
+ <input>
625
+ <port id="0" precision="I32">
626
+ <dim>-1</dim>
627
+ <dim>-1</dim>
628
+ </port>
629
+ </input>
630
+ <output>
631
+ <port id="1" precision="I64" names="attention_mask">
632
+ <dim>-1</dim>
633
+ <dim>-1</dim>
634
+ </port>
635
+ </output>
636
+ </layer>
637
+ <layer id="47" name="RaggedToDense_1947886.0" type="Convert" version="opset1">
638
+ <data destination_type="i64" />
639
+ <input>
640
+ <port id="0" precision="I32">
641
+ <dim>-1</dim>
642
+ <dim>-1</dim>
643
+ </port>
644
+ </input>
645
+ <output>
646
+ <port id="1" precision="I64" names="input_ids">
647
+ <dim>-1</dim>
648
+ <dim>-1</dim>
649
+ </port>
650
+ </output>
651
+ </layer>
652
+ <layer id="48" name="Result_1947890" type="Result" version="opset1" output_names="input_ids">
653
+ <input>
654
+ <port id="0" precision="I64">
655
+ <dim>-1</dim>
656
+ <dim>-1</dim>
657
+ </port>
658
+ </input>
659
+ </layer>
660
+ <layer id="46" name="Result_1947892" type="Result" version="opset1" output_names="attention_mask">
661
+ <input>
662
+ <port id="0" precision="I64">
663
+ <dim>-1</dim>
664
+ <dim>-1</dim>
665
+ </port>
666
+ </input>
667
+ </layer>
668
+ </layers>
669
+ <edges>
670
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
671
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
672
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
673
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
674
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
675
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
676
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
677
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
678
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
679
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
680
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
681
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
682
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
683
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
684
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
685
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
686
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
687
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
688
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
689
+ <edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
690
+ <edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
691
+ <edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
692
+ <edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
693
+ <edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
694
+ <edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
695
+ <edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
696
+ <edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
697
+ <edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
698
+ <edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
699
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
700
+ <edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
701
+ <edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
702
+ <edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
703
+ <edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
704
+ <edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
705
+ <edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
706
+ <edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
707
+ <edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
708
+ <edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
709
+ <edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
710
+ <edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
711
+ <edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
712
+ <edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
713
+ <edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
714
+ <edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
715
+ <edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
716
+ <edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
717
+ <edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
718
+ <edge from-layer="32" from-port="18" to-layer="36" to-port="0" />
719
+ <edge from-layer="32" from-port="19" to-layer="36" to-port="1" />
720
+ <edge from-layer="32" from-port="20" to-layer="36" to-port="2" />
721
+ <edge from-layer="33" from-port="0" to-layer="36" to-port="3" />
722
+ <edge from-layer="34" from-port="0" to-layer="36" to-port="4" />
723
+ <edge from-layer="35" from-port="0" to-layer="36" to-port="5" />
724
+ <edge from-layer="36" from-port="6" to-layer="38" to-port="0" />
725
+ <edge from-layer="36" from-port="8" to-layer="38" to-port="2" />
726
+ <edge from-layer="36" from-port="7" to-layer="38" to-port="1" />
727
+ <edge from-layer="37" from-port="0" to-layer="38" to-port="3" />
728
+ <edge from-layer="38" from-port="5" to-layer="39" to-port="0" />
729
+ <edge from-layer="38" from-port="4" to-layer="39" to-port="1" />
730
+ <edge from-layer="38" from-port="4" to-layer="43" to-port="0" />
731
+ <edge from-layer="38" from-port="5" to-layer="43" to-port="1" />
732
+ <edge from-layer="38" from-port="6" to-layer="43" to-port="2" />
733
+ <edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
734
+ <edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
735
+ <edge from-layer="41" from-port="2" to-layer="43" to-port="3" />
736
+ <edge from-layer="42" from-port="0" to-layer="43" to-port="4" />
737
+ <edge from-layer="43" from-port="6" to-layer="44" to-port="0" />
738
+ <edge from-layer="43" from-port="5" to-layer="47" to-port="0" />
739
+ <edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
740
+ <edge from-layer="45" from-port="1" to-layer="46" to-port="0" />
741
+ <edge from-layer="47" from-port="1" to-layer="48" to-port="0" />
742
+ </edges>
743
+ <rt_info>
744
+ <add_attention_mask value="True" />
745
+ <add_prefix_space />
746
+ <add_special_tokens value="True" />
747
+ <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 %}" />
748
+ <clean_up_tokenization_spaces />
749
+ <detokenizer_input_type value="i64" />
750
+ <eos_token_id value="151645" />
751
+ <handle_special_tokens_with_re />
752
+ <max_length />
753
+ <number_of_inputs value="1" />
754
+ <openvino_tokenizers_version value="2025.4.0.0-625-3694f87878e" />
755
+ <openvino_version value="2025.4.0-20398-7a975177ff4-releases/2025/4" />
756
+ <original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
757
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
758
+ <pad_token_id value="151643" />
759
+ <processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 0]}}" />
760
+ <sentencepiece_version value="0.2.1" />
761
+ <simplified_chat_template value="{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '&lt;|im_start|>system&#10;You are a helpful assistant.&lt;|im_end|>&#10;' }}{% endif %}{{ '&lt;|im_start|>' + message['role'] + '&#10;' + message['content'] + '&lt;|im_end|>' + '&#10;' }}{% endfor %}{% if add_generation_prompt %}{{ '&lt;|im_start|>assistant&#10;' }}{% endif %}" />
762
+ <skip_special_tokens value="True" />
763
+ <streaming_detokenizer value="False" />
764
+ <tiktoken_version value="0.12.0" />
765
+ <tokenizer_output_type value="i64" />
766
+ <tokenizers_version value="0.21.4" />
767
+ <transformers_version value="4.55.4" />
768
+ <use_max_padding value="False" />
769
+ <use_sentencepiece_backend value="False" />
770
+ <utf8_replace_mode value="replace" />
771
+ <with_detokenizer value="True" />
772
+ </rt_info>
773
+ </net>
openvino_vision_embeddings_merger_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14335ae8af84181781e09be1024f17151e042e66c4a0d99bf2ba822096e68815
3
+ size 676591800
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 sha256:7ee95d6c45270dd3de95fbbb0042714154bed90b5f95d8df1e9af9c313c0ddaf
3
+ size 1507896
openvino_vision_embeddings_model.xml ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_93793" 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_1,input">
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_1168312" 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_93840" 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_93867" type="Result" version="opset1" output_names="last_hidden_state">
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="2025.4.0-20398-7a975177ff4-releases/2025/4" />
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
+ <version value="2.19.0" />
224
+ <weight_compression>
225
+ <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}" />
226
+ <all_layers value="False" />
227
+ <awq value="False" />
228
+ <backup_mode value="int8_asym" />
229
+ <compression_format value="dequantize" />
230
+ <gptq value="False" />
231
+ <group_size value="-1" />
232
+ <ignored_scope value="[]" />
233
+ <lora_correction value="False" />
234
+ <mode value="int8_sym" />
235
+ <ratio value="1.0" />
236
+ <scale_estimation value="False" />
237
+ <sensitivity_metric value="weight_quantization_error" />
238
+ </weight_compression>
239
+ </nncf>
240
+ <optimum>
241
+ <nncf_version value="2.19.0.dev0+473ef3228" />
242
+ <optimum_intel_version value="1.27.0.dev0+906008d" />
243
+ <optimum_version value="2.0.0" />
244
+ <pytorch_version value="2.9.1+cpu" />
245
+ <transformers_version value="4.55.4" />
246
+ </optimum>
247
+ </rt_info>
248
+ </net>
preprocessor_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessorFast",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_pixels": 12845056,
25
+ "merge_size": 2,
26
+ "min_pixels": 3136,
27
+ "patch_size": 14,
28
+ "processor_class": "Qwen2_5_VLProcessor",
29
+ "resample": 3,
30
+ "rescale_factor": 0.00392156862745098,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "longest_edge": 12845056,
34
+ "shortest_edge": 3136
35
+ },
36
+ "temporal_patch_size": 2
37
+ }
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_frames": 768,
26
+ "max_pixels": 12845056,
27
+ "merge_size": 2,
28
+ "min_frames": 4,
29
+ "min_pixels": 3136,
30
+ "num_frames": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "size": {
36
+ "longest_edge": 12845056,
37
+ "shortest_edge": 3136
38
+ },
39
+ "size_divisor": null,
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff