Hugging Face's logo

OpenVINO
/
InternVL2-1B-fp16-ov

Image-Text-to-Text
OpenVINO
multilingual
internvl_chat
nlp
vision
internvl
conversational
custom_code
Model card Files Community
katuni4ka commited on
Commit
c0b0759
·
verified ·
1 Parent(s): f9bfa6a

Upload 20 files

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. README.md +141 -0
  3. added_tokens.json +14 -0
  4. config.json +196 -0
  5. generation_config.json +8 -0
  6. merges.txt +0 -0
  7. openvino_detokenizer.bin +3 -0
  8. openvino_detokenizer.xml +279 -0
  9. openvino_language_model.bin +3 -0
  10. openvino_language_model.xml +0 -0
  11. openvino_text_embeddings_model.bin +3 -0
  12. openvino_text_embeddings_model.xml +113 -0
  13. openvino_tokenizer.bin +3 -0
  14. openvino_tokenizer.xml +719 -0
  15. openvino_vision_embeddings_model.bin +3 -0
  16. openvino_vision_embeddings_model.xml +0 -0
  17. preprocessor_config.json +27 -0
  18. special_tokens_map.json +29 -0
  19. tokenizer.json +3 -0
  20. tokenizer_config.json +126 -0
  21. 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 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - multilingual
5
+ pipeline_tag: image-text-to-text
6
+ tags:
7
+ - nlp
8
+ - vision
9
+ - internvl
10
+ base_model:
11
+ - OpenGVLab/InternVL2-1B
12
+ ---
13
+
14
+ # InternVL2-1B-fp16-ov
15
+
16
+ * Model creator: [OpenGVLab](https://huggingface.co/OpenGVLab)
17
+ * Original model: [InternVL2-1B](https://huggingface.co/OpenGVLab/InternVL2-1B)
18
+
19
+ ## Description
20
+
21
+ This is [OpenGVLab/InternVL2-1B](https://huggingface.co/OpenGVLab/InternVL2-1B) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format.
22
+
23
+
24
+ ## Compatibility
25
+
26
+ The provided OpenVINO™ IR model is compatible with:
27
+
28
+ * OpenVINO version 2025.0.0 and higher
29
+ * Optimum Intel 1.21.0 and higher
30
+
31
+ ## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
32
+
33
+ 1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
34
+
35
+ ```
36
+ pip install --pre -U --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release openvino_tokenizers openvino
37
+
38
+ pip install git+https://github.com/huggingface/optimum-intel.git
39
+ ```
40
+
41
+ 2. Run model inference
42
+
43
+ ```
44
+ from PIL import Image
45
+ import requests
46
+ from optimum.intel.openvino import OVModelForVisualCausalLM
47
+ from transformers import AutoTokenizer, TextStreamer
48
+
49
+ model_id = "OpenVINO/InternVL2-1B-fp16-ov"
50
+
51
+ tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
52
+
53
+ ov_model = OVModelForVisualCausalLM.from_pretrained(model_id, trust_remote_code=True)
54
+ prompt = "What is unusual on this picture?"
55
+
56
+ url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
57
+ image = Image.open(requests.get(url, stream=True).raw)
58
+
59
+ inputs = ov_model.preprocess_inputs(text=prompt, image=image, tokenizer=tokenizer, config=ov_model.config)
60
+
61
+ generation_args = {
62
+ "max_new_tokens": 100,
63
+ "streamer": TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
64
+ }
65
+
66
+ generate_ids = ov_model.generate(**inputs, **generation_args)
67
+
68
+ generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
69
+ response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True)[0]
70
+
71
+ ```
72
+
73
+ ## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
74
+
75
+ 1. Install packages required for using OpenVINO GenAI.
76
+ ```
77
+ pip install --pre -U --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/pre-release openvino openvino-tokenizers openvino-genai
78
+
79
+ pip install huggingface_hub
80
+ ```
81
+
82
+ 2. Download model from HuggingFace Hub
83
+
84
+ ```
85
+ import huggingface_hub as hf_hub
86
+
87
+ model_id = "OpenVINO/InternVL2-1B-fp16-ov"
88
+ model_path = "InternVL2-1B-fp16-ov"
89
+
90
+ hf_hub.snapshot_download(model_id, local_dir=model_path)
91
+
92
+ ```
93
+
94
+ 1. Run model inference:
95
+
96
+ ```
97
+ import openvino_genai as ov_genai
98
+ import requests
99
+ from PIL import Image
100
+ from io import BytesIO
101
+ import numpy as np
102
+ import openvino as ov
103
+
104
+ device = "CPU"
105
+ pipe = ov_genai.VLMPipeline(model_path, device)
106
+
107
+ def load_image(image_file):
108
+ if isinstance(image_file, str) and (image_file.startswith("http") or image_file.startswith("https")):
109
+ response = requests.get(image_file)
110
+ image = Image.open(BytesIO(response.content)).convert("RGB")
111
+ else:
112
+ image = Image.open(image_file).convert("RGB")
113
+ image_data = np.array(image.getdata()).reshape(1, image.size[1], image.size[0], 3).astype(np.byte)
114
+ return ov.Tensor(image_data)
115
+
116
+ prompt = "What is unusual on this picture?"
117
+
118
+ url = "https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11"
119
+ image_tensor = load_image(url)
120
+
121
+ def streamer(subword: str) -> bool:
122
+ print(subword, end="", flush=True)
123
+ return False
124
+
125
+ pipe.start_chat()
126
+ output = pipe.generate(prompt, image=image_tensor, max_new_tokens=100, streamer=streamer)
127
+ pipe.start_chat()
128
+ ```
129
+
130
+ 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)
131
+
132
+
133
+ ## Limitations
134
+
135
+
136
+ Check the original [model card](https://huggingface.co/OpenGVLab/InternVL2-1B) for limitations.
137
+
138
+ ## Legal information
139
+
140
+ The original model is distributed under [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) license. More details can be found in [original model card](https://huggingface.co/OpenGVLab/InternVL2-1B).
141
+
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151654,
3
+ "</img>": 151647,
4
+ "</quad>": 151650,
5
+ "</ref>": 151652,
6
+ "<IMG_CONTEXT>": 151648,
7
+ "<box>": 151653,
8
+ "<img>": 151646,
9
+ "<quad>": 151649,
10
+ "<ref>": 151651,
11
+ "<|endoftext|>": 151643,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644
14
+ }
config.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_commit_hash": "3bc2e85347e17591b9387f283fef91b985b770c3",
4
+ "_name_or_path": "OpenGVLab/InternVL2-1B",
5
+ "architectures": [
6
+ "InternVLChatModel"
7
+ ],
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
10
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
11
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
12
+ },
13
+ "downsample_ratio": 0.5,
14
+ "dynamic_image_size": true,
15
+ "force_image_size": 448,
16
+ "img_context_token_id": 151648,
17
+ "llm_config": {
18
+ "_attn_implementation_autoset": true,
19
+ "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
20
+ "add_cross_attention": false,
21
+ "architectures": [
22
+ "Qwen2ForCausalLM"
23
+ ],
24
+ "attention_dropout": 0.0,
25
+ "bad_words_ids": null,
26
+ "begin_suppress_tokens": null,
27
+ "bos_token_id": 151643,
28
+ "chunk_size_feed_forward": 0,
29
+ "cross_attention_hidden_size": null,
30
+ "decoder_start_token_id": null,
31
+ "diversity_penalty": 0.0,
32
+ "do_sample": false,
33
+ "early_stopping": false,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 151645,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 896,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 4864,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 32768,
57
+ "max_window_layers": 24,
58
+ "min_length": 0,
59
+ "model_type": "qwen2",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_attention_heads": 14,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_hidden_layers": 24,
65
+ "num_key_value_heads": 2,
66
+ "num_return_sequences": 1,
67
+ "output_attentions": false,
68
+ "output_hidden_states": false,
69
+ "output_scores": false,
70
+ "pad_token_id": null,
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "rms_norm_eps": 1e-06,
79
+ "rope_scaling": null,
80
+ "rope_theta": 1000000.0,
81
+ "sep_token_id": null,
82
+ "sliding_window": null,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": false,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": "bfloat16",
93
+ "torchscript": false,
94
+ "transformers_version": "4.47.0",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": true,
97
+ "use_cache": true,
98
+ "use_sliding_window": false,
99
+ "vocab_size": 151655
100
+ },
101
+ "max_dynamic_patch": 12,
102
+ "min_dynamic_patch": 1,
103
+ "model_type": "internvl_chat",
104
+ "ps_version": "v2",
105
+ "select_layer": -1,
106
+ "template": "Hermes-2",
107
+ "transformers_version": null,
108
+ "use_backbone_lora": 0,
109
+ "use_llm_lora": 0,
110
+ "use_thumbnail": true,
111
+ "vision_config": {
112
+ "_attn_implementation_autoset": true,
113
+ "_name_or_path": "",
114
+ "add_cross_attention": false,
115
+ "architectures": [
116
+ "InternVisionModel"
117
+ ],
118
+ "attention_dropout": 0.0,
119
+ "bad_words_ids": null,
120
+ "begin_suppress_tokens": null,
121
+ "bos_token_id": null,
122
+ "chunk_size_feed_forward": 0,
123
+ "cross_attention_hidden_size": null,
124
+ "decoder_start_token_id": null,
125
+ "diversity_penalty": 0.0,
126
+ "do_sample": false,
127
+ "drop_path_rate": 0.0,
128
+ "dropout": 0.0,
129
+ "early_stopping": false,
130
+ "encoder_no_repeat_ngram_size": 0,
131
+ "eos_token_id": null,
132
+ "exponential_decay_length_penalty": null,
133
+ "finetuning_task": null,
134
+ "forced_bos_token_id": null,
135
+ "forced_eos_token_id": null,
136
+ "hidden_act": "gelu",
137
+ "hidden_size": 1024,
138
+ "id2label": {
139
+ "0": "LABEL_0",
140
+ "1": "LABEL_1"
141
+ },
142
+ "image_size": 448,
143
+ "initializer_factor": 1.0,
144
+ "initializer_range": 0.02,
145
+ "intermediate_size": 4096,
146
+ "is_decoder": false,
147
+ "is_encoder_decoder": false,
148
+ "label2id": {
149
+ "LABEL_0": 0,
150
+ "LABEL_1": 1
151
+ },
152
+ "layer_norm_eps": 1e-06,
153
+ "length_penalty": 1.0,
154
+ "max_length": 20,
155
+ "min_length": 0,
156
+ "model_type": "intern_vit_6b",
157
+ "no_repeat_ngram_size": 0,
158
+ "norm_type": "layer_norm",
159
+ "num_attention_heads": 16,
160
+ "num_beam_groups": 1,
161
+ "num_beams": 1,
162
+ "num_channels": 3,
163
+ "num_hidden_layers": 24,
164
+ "num_return_sequences": 1,
165
+ "output_attentions": false,
166
+ "output_hidden_states": false,
167
+ "output_scores": false,
168
+ "pad_token_id": null,
169
+ "patch_size": 14,
170
+ "prefix": null,
171
+ "problem_type": null,
172
+ "pruned_heads": {},
173
+ "qk_normalization": false,
174
+ "qkv_bias": true,
175
+ "remove_invalid_values": false,
176
+ "repetition_penalty": 1.0,
177
+ "return_dict": true,
178
+ "return_dict_in_generate": false,
179
+ "sep_token_id": null,
180
+ "suppress_tokens": null,
181
+ "task_specific_params": null,
182
+ "temperature": 1.0,
183
+ "tf_legacy_loss": false,
184
+ "tie_encoder_decoder": false,
185
+ "tie_word_embeddings": true,
186
+ "tokenizer_class": null,
187
+ "top_k": 50,
188
+ "top_p": 1.0,
189
+ "torch_dtype": "bfloat16",
190
+ "torchscript": false,
191
+ "transformers_version": "4.47.0",
192
+ "typical_p": 1.0,
193
+ "use_bfloat16": true,
194
+ "use_flash_attn": false
195
+ }
196
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151644,
5
+ 151645
6
+ ],
7
+ "transformers_version": "4.47.0"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
openvino_detokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75fa1f91293966b14a7e48d848bf123b5478c286d745dcb79b042a2a3ab63cc
3
+ size 2189371
openvino_detokenizer.xml ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="detokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_103781" type="Parameter" version="opset1">
5
+ <data shape="?,?" element_type="i64" />
6
+ <output>
7
+ <port id="0" precision="I64" names="Parameter_103781">
8
+ <dim>-1</dim>
9
+ <dim>-1</dim>
10
+ </port>
11
+ </output>
12
+ </layer>
13
+ <layer id="1" name="Convert_103797" 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_103744" type="Const" version="opset1">
29
+ <data element_type="i32" shape="151655" offset="0" size="606620" />
30
+ <output>
31
+ <port id="0" precision="I32">
32
+ <dim>151655</dim>
33
+ </port>
34
+ </output>
35
+ </layer>
36
+ <layer id="3" name="Constant_103746" type="Const" version="opset1">
37
+ <data element_type="i32" shape="151655" offset="606620" size="606620" />
38
+ <output>
39
+ <port id="0" precision="I32">
40
+ <dim>151655</dim>
41
+ </port>
42
+ </output>
43
+ </layer>
44
+ <layer id="4" name="Constant_103748" type="Const" version="opset1">
45
+ <data element_type="u8" shape="976063" offset="1213240" size="976063" />
46
+ <output>
47
+ <port id="0" precision="U8">
48
+ <dim>976063</dim>
49
+ </port>
50
+ </output>
51
+ </layer>
52
+ <layer id="5" name="Constant_103785" type="Const" version="opset1">
53
+ <data element_type="i32" shape="12" offset="2189303" size="48" />
54
+ <output>
55
+ <port id="0" precision="I32">
56
+ <dim>12</dim>
57
+ </port>
58
+ </output>
59
+ </layer>
60
+ <layer id="6" name="Constant_103783" type="Const" version="opset1">
61
+ <data element_type="i32" shape="1" offset="2189351" size="4" />
62
+ <output>
63
+ <port id="0" precision="I32">
64
+ <dim>1</dim>
65
+ </port>
66
+ </output>
67
+ </layer>
68
+ <layer id="7" name="Constant_103782" type="Const" version="opset1">
69
+ <data element_type="i32" shape="1" offset="2189355" size="4" />
70
+ <output>
71
+ <port id="0" precision="I32">
72
+ <dim>1</dim>
73
+ </port>
74
+ </output>
75
+ </layer>
76
+ <layer id="8" name="Constant_103784" type="Const" version="opset1">
77
+ <data element_type="i32" shape="1" offset="2189359" size="4" />
78
+ <output>
79
+ <port id="0" precision="I32">
80
+ <dim>1</dim>
81
+ </port>
82
+ </output>
83
+ </layer>
84
+ <layer id="9" name="Constant_103787" type="Const" version="opset1">
85
+ <data element_type="i64" shape="1" offset="2189363" size="8" />
86
+ <output>
87
+ <port id="0" precision="I64">
88
+ <dim>1</dim>
89
+ </port>
90
+ </output>
91
+ </layer>
92
+ <layer id="10" name="Slice_103786" type="Slice" version="opset8">
93
+ <input>
94
+ <port id="0" precision="I32">
95
+ <dim>12</dim>
96
+ </port>
97
+ <port id="1" precision="I32">
98
+ <dim>1</dim>
99
+ </port>
100
+ <port id="2" precision="I32">
101
+ <dim>1</dim>
102
+ </port>
103
+ <port id="3" precision="I32">
104
+ <dim>1</dim>
105
+ </port>
106
+ <port id="4" precision="I64">
107
+ <dim>1</dim>
108
+ </port>
109
+ </input>
110
+ <output>
111
+ <port id="5" precision="I32">
112
+ <dim>12</dim>
113
+ </port>
114
+ </output>
115
+ </layer>
116
+ <layer id="11" name="VocabDecoder_103788" type="VocabDecoder" version="extension">
117
+ <data skip_tokens="" />
118
+ <input>
119
+ <port id="0" precision="I32">
120
+ <dim>-1</dim>
121
+ <dim>-1</dim>
122
+ </port>
123
+ <port id="1" precision="I32">
124
+ <dim>151655</dim>
125
+ </port>
126
+ <port id="2" precision="I32">
127
+ <dim>151655</dim>
128
+ </port>
129
+ <port id="3" precision="U8">
130
+ <dim>976063</dim>
131
+ </port>
132
+ <port id="4" precision="I32">
133
+ <dim>12</dim>
134
+ </port>
135
+ </input>
136
+ <output>
137
+ <port id="5" precision="I32">
138
+ <dim>-1</dim>
139
+ </port>
140
+ <port id="6" precision="I32">
141
+ <dim>-1</dim>
142
+ </port>
143
+ <port id="7" precision="I32">
144
+ <dim>-1</dim>
145
+ </port>
146
+ <port id="8" precision="I32">
147
+ <dim>-1</dim>
148
+ </port>
149
+ <port id="9" precision="U8">
150
+ <dim>-1</dim>
151
+ </port>
152
+ </output>
153
+ </layer>
154
+ <layer id="12" name="FuzeRagged_103789" type="FuzeRagged" version="extension">
155
+ <input>
156
+ <port id="0" precision="I32">
157
+ <dim>-1</dim>
158
+ </port>
159
+ <port id="1" precision="I32">
160
+ <dim>-1</dim>
161
+ </port>
162
+ <port id="2" precision="I32">
163
+ <dim>-1</dim>
164
+ </port>
165
+ <port id="3" precision="I32">
166
+ <dim>-1</dim>
167
+ </port>
168
+ </input>
169
+ <output>
170
+ <port id="4" precision="I32">
171
+ <dim>-1</dim>
172
+ </port>
173
+ <port id="5" precision="I32">
174
+ <dim>-1</dim>
175
+ </port>
176
+ </output>
177
+ </layer>
178
+ <layer id="13" name="UTF8Validate_103790" type="UTF8Validate" version="extension">
179
+ <data replace_mode="true" />
180
+ <input>
181
+ <port id="0" precision="I32">
182
+ <dim>-1</dim>
183
+ </port>
184
+ <port id="1" precision="I32">
185
+ <dim>-1</dim>
186
+ </port>
187
+ <port id="2" precision="U8">
188
+ <dim>-1</dim>
189
+ </port>
190
+ </input>
191
+ <output>
192
+ <port id="3" precision="I32">
193
+ <dim>-1</dim>
194
+ </port>
195
+ <port id="4" precision="I32">
196
+ <dim>-1</dim>
197
+ </port>
198
+ <port id="5" precision="U8">
199
+ <dim>-1</dim>
200
+ </port>
201
+ </output>
202
+ </layer>
203
+ <layer id="14" name="StringTensorPack_103791" type="StringTensorPack" version="opset15">
204
+ <input>
205
+ <port id="0" precision="I32">
206
+ <dim>-1</dim>
207
+ </port>
208
+ <port id="1" precision="I32">
209
+ <dim>-1</dim>
210
+ </port>
211
+ <port id="2" precision="U8">
212
+ <dim>-1</dim>
213
+ </port>
214
+ </input>
215
+ <output>
216
+ <port id="3" precision="STRING" names="string_output">
217
+ <dim>-1</dim>
218
+ </port>
219
+ </output>
220
+ </layer>
221
+ <layer id="15" name="Result_103792" type="Result" version="opset1">
222
+ <input>
223
+ <port id="0" precision="STRING">
224
+ <dim>-1</dim>
225
+ </port>
226
+ </input>
227
+ </layer>
228
+ </layers>
229
+ <edges>
230
+ <edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
231
+ <edge from-layer="1" from-port="1" to-layer="11" to-port="0" />
232
+ <edge from-layer="2" from-port="0" to-layer="11" to-port="1" />
233
+ <edge from-layer="3" from-port="0" to-layer="11" to-port="2" />
234
+ <edge from-layer="4" from-port="0" to-layer="11" to-port="3" />
235
+ <edge from-layer="5" from-port="0" to-layer="10" to-port="0" />
236
+ <edge from-layer="6" from-port="0" to-layer="10" to-port="1" />
237
+ <edge from-layer="7" from-port="0" to-layer="10" to-port="2" />
238
+ <edge from-layer="8" from-port="0" to-layer="10" to-port="3" />
239
+ <edge from-layer="9" from-port="0" to-layer="10" to-port="4" />
240
+ <edge from-layer="10" from-port="5" to-layer="11" to-port="4" />
241
+ <edge from-layer="11" from-port="5" to-layer="12" to-port="0" />
242
+ <edge from-layer="11" from-port="9" to-layer="13" to-port="2" />
243
+ <edge from-layer="11" from-port="8" to-layer="12" to-port="3" />
244
+ <edge from-layer="11" from-port="7" to-layer="12" to-port="2" />
245
+ <edge from-layer="11" from-port="6" to-layer="12" to-port="1" />
246
+ <edge from-layer="12" from-port="4" to-layer="13" to-port="0" />
247
+ <edge from-layer="12" from-port="5" to-layer="13" to-port="1" />
248
+ <edge from-layer="13" from-port="3" to-layer="14" to-port="0" />
249
+ <edge from-layer="13" from-port="4" to-layer="14" to-port="1" />
250
+ <edge from-layer="13" from-port="5" to-layer="14" to-port="2" />
251
+ <edge from-layer="14" from-port="3" to-layer="15" to-port="0" />
252
+ </edges>
253
+ <rt_info>
254
+ <add_attention_mask value="True" />
255
+ <add_prefix_space />
256
+ <add_special_tokens value="True" />
257
+ <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 %}" />
258
+ <clean_up_tokenization_spaces />
259
+ <detokenizer_input_type value="i64" />
260
+ <eos_token_id value="151645" />
261
+ <handle_special_tokens_with_re />
262
+ <number_of_inputs value="1" />
263
+ <openvino_tokenizers_version value="2025.0.0.0-471-7f2ac4f9648" />
264
+ <openvino_version value="2025.0.0-17908-513dcc5c7b7-releases/2025/0" />
265
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
266
+ <pad_token_id value="151643" />
267
+ <sentencepiece_version value="0.2.0" />
268
+ <skip_special_tokens value="True" />
269
+ <streaming_detokenizer value="False" />
270
+ <tiktoken_version value="0.7.0" />
271
+ <tokenizer_output_type value="i64" />
272
+ <tokenizers_version value="0.21.0" />
273
+ <transformers_version value="4.47.0" />
274
+ <use_max_padding value="False" />
275
+ <use_sentencepiece_backend value="False" />
276
+ <utf8_replace_mode value="replace" />
277
+ <with_detokenizer value="True" />
278
+ </rt_info>
279
+ </net>
openvino_language_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eaa40ebc46b0b2e7cae75d4338b5c76cb6ce4857a326a697a0c869bffffde9
3
+ size 987562336
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:dfd52b2ca52642452c5d9b3e530a64ae7a5a2f23659838755f5354415bffa762
3
+ size 271765764
openvino_text_embeddings_model.xml ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="Model6" 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_compressed" type="Const" version="opset1">
14
+ <data element_type="f16" shape="151655, 896" offset="0" size="271765760" />
15
+ <output>
16
+ <port id="0" precision="FP16" names="self.weight">
17
+ <dim>151655</dim>
18
+ <dim>896</dim>
19
+ </port>
20
+ </output>
21
+ </layer>
22
+ <layer id="2" name="self.weight" type="Convert" version="opset1">
23
+ <data destination_type="f32" />
24
+ <rt_info>
25
+ <attribute name="decompression" version="0" />
26
+ </rt_info>
27
+ <input>
28
+ <port id="0" precision="FP16">
29
+ <dim>151655</dim>
30
+ <dim>896</dim>
31
+ </port>
32
+ </input>
33
+ <output>
34
+ <port id="1" precision="FP32">
35
+ <dim>151655</dim>
36
+ <dim>896</dim>
37
+ </port>
38
+ </output>
39
+ </layer>
40
+ <layer id="3" name="aten::embedding/Convert" type="Convert" version="opset1">
41
+ <data destination_type="i32" />
42
+ <input>
43
+ <port id="0" precision="I64">
44
+ <dim>-1</dim>
45
+ <dim>-1</dim>
46
+ </port>
47
+ </input>
48
+ <output>
49
+ <port id="1" precision="I32">
50
+ <dim>-1</dim>
51
+ <dim>-1</dim>
52
+ </port>
53
+ </output>
54
+ </layer>
55
+ <layer id="4" name="aten::embedding/Constant" type="Const" version="opset1">
56
+ <data element_type="i32" shape="" offset="271765760" size="4" />
57
+ <output>
58
+ <port id="0" precision="I32" />
59
+ </output>
60
+ </layer>
61
+ <layer id="5" name="aten::embedding/Gather" type="Gather" version="opset8">
62
+ <data batch_dims="0" />
63
+ <input>
64
+ <port id="0" precision="FP32">
65
+ <dim>151655</dim>
66
+ <dim>896</dim>
67
+ </port>
68
+ <port id="1" precision="I32">
69
+ <dim>-1</dim>
70
+ <dim>-1</dim>
71
+ </port>
72
+ <port id="2" precision="I32" />
73
+ </input>
74
+ <output>
75
+ <port id="3" precision="FP32" names="inputs_embeds">
76
+ <dim>-1</dim>
77
+ <dim>-1</dim>
78
+ <dim>896</dim>
79
+ </port>
80
+ </output>
81
+ </layer>
82
+ <layer id="6" name="Result_101891" type="Result" version="opset1">
83
+ <input>
84
+ <port id="0" precision="FP32">
85
+ <dim>-1</dim>
86
+ <dim>-1</dim>
87
+ <dim>896</dim>
88
+ </port>
89
+ </input>
90
+ </layer>
91
+ </layers>
92
+ <edges>
93
+ <edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
94
+ <edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
95
+ <edge from-layer="2" from-port="1" to-layer="5" to-port="0" />
96
+ <edge from-layer="3" from-port="1" to-layer="5" to-port="1" />
97
+ <edge from-layer="4" from-port="0" to-layer="5" to-port="2" />
98
+ <edge from-layer="5" from-port="3" to-layer="6" to-port="0" />
99
+ </edges>
100
+ <rt_info>
101
+ <Runtime_version value="2025.0.0-17908-513dcc5c7b7-releases/2025/0" />
102
+ <conversion_parameters>
103
+ <framework value="pytorch" />
104
+ <is_python_object value="True" />
105
+ </conversion_parameters>
106
+ <optimum>
107
+ <optimum_intel_version value="1.22.0.dev0+2b0d642" />
108
+ <optimum_version value="1.24.0.dev0" />
109
+ <pytorch_version value="2.5.1+cpu" />
110
+ <transformers_version value="4.47.0" />
111
+ </optimum>
112
+ </rt_info>
113
+ </net>
openvino_tokenizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3a335c7a9e16bcc547408ea0e61cda12049f13d512689757a358310492ace17
3
+ size 5584911
openvino_tokenizer.xml ADDED
@@ -0,0 +1,719 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <?xml version="1.0"?>
2
+ <net name="tokenizer" version="11">
3
+ <layers>
4
+ <layer id="0" name="Parameter_103662" type="Parameter" version="opset1">
5
+ <data shape="?" element_type="string" />
6
+ <output>
7
+ <port id="0" precision="STRING" names="Parameter_103662">
8
+ <dim>-1</dim>
9
+ </port>
10
+ </output>
11
+ </layer>
12
+ <layer id="1" name="Constant_103668" 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_103663" 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_103664" 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_103665" 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_103666" 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_103667" 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_103669" 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_103670" 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_103671" 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_103672" 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_103673" 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_103674" 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_103675" 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_103737" type="Const" version="opset1">
135
+ <data element_type="u8" shape="163" offset="16" size="163" />
136
+ <output>
137
+ <port id="0" precision="U8">
138
+ <dim>163</dim>
139
+ </port>
140
+ </output>
141
+ </layer>
142
+ <layer id="15" name="SpecialTokensSplit_103738" 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>163</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="NormalizeUnicode_103739" type="NormalizeUnicode" version="extension">
185
+ <data normalization_form="NFC" />
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_103741" type="Const" version="opset1">
216
+ <data element_type="u8" shape="110" offset="179" 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_103742" 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_103744" type="Const" version="opset1">
270
+ <data element_type="i32" shape="151655" offset="289" size="606620" />
271
+ <output>
272
+ <port id="0" precision="I32">
273
+ <dim>151655</dim>
274
+ </port>
275
+ </output>
276
+ </layer>
277
+ <layer id="20" name="Constant_103746" type="Const" version="opset1">
278
+ <data element_type="i32" shape="151655" offset="606909" size="606620" />
279
+ <output>
280
+ <port id="0" precision="I32">
281
+ <dim>151655</dim>
282
+ </port>
283
+ </output>
284
+ </layer>
285
+ <layer id="21" name="Constant_103748" type="Const" version="opset1">
286
+ <data element_type="u8" shape="976063" offset="1213529" size="976063" />
287
+ <output>
288
+ <port id="0" precision="U8">
289
+ <dim>976063</dim>
290
+ </port>
291
+ </output>
292
+ </layer>
293
+ <layer id="22" name="Constant_103756" type="Const" version="opset1">
294
+ <data element_type="i32" shape="151291" offset="2189592" size="605164" />
295
+ <output>
296
+ <port id="0" precision="I32">
297
+ <dim>151291</dim>
298
+ </port>
299
+ </output>
300
+ </layer>
301
+ <layer id="23" name="Constant_103758" type="Const" version="opset1">
302
+ <data element_type="i32" shape="151291" offset="2794756" size="605164" />
303
+ <output>
304
+ <port id="0" precision="I32">
305
+ <dim>151291</dim>
306
+ </port>
307
+ </output>
308
+ </layer>
309
+ <layer id="24" name="Constant_103760" type="Const" version="opset1">
310
+ <data element_type="u8" shape="490634" offset="3399920" size="490634" />
311
+ <output>
312
+ <port id="0" precision="U8">
313
+ <dim>490634</dim>
314
+ </port>
315
+ </output>
316
+ </layer>
317
+ <layer id="25" name="Constant_103762" type="Const" version="opset1">
318
+ <data element_type="i32" shape="151291" offset="3890554" size="605164" />
319
+ <output>
320
+ <port id="0" precision="I32">
321
+ <dim>151291</dim>
322
+ </port>
323
+ </output>
324
+ </layer>
325
+ <layer id="26" name="Constant_103764" type="Const" version="opset1">
326
+ <data element_type="i32" shape="151291" offset="4495718" size="605164" />
327
+ <output>
328
+ <port id="0" precision="I32">
329
+ <dim>151291</dim>
330
+ </port>
331
+ </output>
332
+ </layer>
333
+ <layer id="27" name="Constant_103766" type="Const" version="opset1">
334
+ <data element_type="u8" shape="483779" offset="5100882" size="483779" />
335
+ <output>
336
+ <port id="0" precision="U8">
337
+ <dim>483779</dim>
338
+ </port>
339
+ </output>
340
+ </layer>
341
+ <layer id="28" name="Constant_103750" type="Const" version="opset1">
342
+ <data element_type="i32" shape="12" offset="5584661" size="48" />
343
+ <output>
344
+ <port id="0" precision="I32">
345
+ <dim>12</dim>
346
+ </port>
347
+ </output>
348
+ </layer>
349
+ <layer id="29" name="Constant_103752" type="Const" version="opset1">
350
+ <data element_type="i32" shape="12" offset="5584709" size="48" />
351
+ <output>
352
+ <port id="0" precision="I32">
353
+ <dim>12</dim>
354
+ </port>
355
+ </output>
356
+ </layer>
357
+ <layer id="30" name="Constant_103754" type="Const" version="opset1">
358
+ <data element_type="u8" shape="94" offset="5584757" size="94" />
359
+ <output>
360
+ <port id="0" precision="U8">
361
+ <dim>94</dim>
362
+ </port>
363
+ </output>
364
+ </layer>
365
+ <layer id="31" name="Constant_103767" type="Const" version="opset1">
366
+ <data element_type="i32" shape="12" offset="5584851" size="48" />
367
+ <output>
368
+ <port id="0" precision="I32">
369
+ <dim>12</dim>
370
+ </port>
371
+ </output>
372
+ </layer>
373
+ <layer id="32" name="BPETokenizer_103768" 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>151655</dim>
393
+ </port>
394
+ <port id="6" precision="I32">
395
+ <dim>151655</dim>
396
+ </port>
397
+ <port id="7" precision="U8">
398
+ <dim>976063</dim>
399
+ </port>
400
+ <port id="8" precision="I32">
401
+ <dim>151291</dim>
402
+ </port>
403
+ <port id="9" precision="I32">
404
+ <dim>151291</dim>
405
+ </port>
406
+ <port id="10" precision="U8">
407
+ <dim>490634</dim>
408
+ </port>
409
+ <port id="11" precision="I32">
410
+ <dim>151291</dim>
411
+ </port>
412
+ <port id="12" precision="I32">
413
+ <dim>151291</dim>
414
+ </port>
415
+ <port id="13" precision="U8">
416
+ <dim>483779</dim>
417
+ </port>
418
+ <port id="14" precision="I32">
419
+ <dim>12</dim>
420
+ </port>
421
+ <port id="15" precision="I32">
422
+ <dim>12</dim>
423
+ </port>
424
+ <port id="16" precision="U8">
425
+ <dim>94</dim>
426
+ </port>
427
+ <port id="17" precision="I32">
428
+ <dim>12</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="Subtract_103769" type="Subtract" version="opset1">
444
+ <data auto_broadcast="numpy" />
445
+ <input>
446
+ <port id="0" precision="I32">
447
+ <dim>-1</dim>
448
+ </port>
449
+ <port id="1" precision="I32">
450
+ <dim>-1</dim>
451
+ </port>
452
+ </input>
453
+ <output>
454
+ <port id="2" precision="I32">
455
+ <dim>-1</dim>
456
+ </port>
457
+ </output>
458
+ </layer>
459
+ <layer id="34" name="Constant_103770" type="Const" version="opset1">
460
+ <data element_type="i32" shape="" offset="5584899" size="4" />
461
+ <output>
462
+ <port id="0" precision="I32" />
463
+ </output>
464
+ </layer>
465
+ <layer id="35" name="Minimum_103771" type="Minimum" version="opset1">
466
+ <data auto_broadcast="numpy" />
467
+ <input>
468
+ <port id="0" precision="I32">
469
+ <dim>-1</dim>
470
+ </port>
471
+ <port id="1" precision="I32" />
472
+ </input>
473
+ <output>
474
+ <port id="2" precision="I32">
475
+ <dim>-1</dim>
476
+ </port>
477
+ </output>
478
+ </layer>
479
+ <layer id="36" name="Add_103772" type="Add" version="opset1">
480
+ <data auto_broadcast="numpy" />
481
+ <input>
482
+ <port id="0" precision="I32">
483
+ <dim>-1</dim>
484
+ </port>
485
+ <port id="1" precision="I32">
486
+ <dim>-1</dim>
487
+ </port>
488
+ </input>
489
+ <output>
490
+ <port id="2" precision="I32">
491
+ <dim>-1</dim>
492
+ </port>
493
+ </output>
494
+ </layer>
495
+ <layer id="37" name="Subtract_103773" type="Subtract" version="opset1">
496
+ <data auto_broadcast="numpy" />
497
+ <input>
498
+ <port id="0" precision="I32">
499
+ <dim>-1</dim>
500
+ </port>
501
+ <port id="1" precision="I32">
502
+ <dim>-1</dim>
503
+ </port>
504
+ </input>
505
+ <output>
506
+ <port id="2" precision="I32">
507
+ <dim>-1</dim>
508
+ </port>
509
+ </output>
510
+ </layer>
511
+ <layer id="38" name="Constant_103774" type="Const" version="opset1">
512
+ <data element_type="i32" shape="" offset="5584903" size="4" />
513
+ <output>
514
+ <port id="0" precision="I32" />
515
+ </output>
516
+ </layer>
517
+ <layer id="39" name="ReduceMax_103775" type="ReduceMax" version="opset1">
518
+ <data keep_dims="false" />
519
+ <input>
520
+ <port id="0" precision="I32">
521
+ <dim>-1</dim>
522
+ </port>
523
+ <port id="1" precision="I32" />
524
+ </input>
525
+ <output>
526
+ <port id="2" precision="I32" />
527
+ </output>
528
+ </layer>
529
+ <layer id="40" name="Constant_103776" type="Const" version="opset1">
530
+ <data element_type="i32" shape="" offset="5584907" size="4" />
531
+ <output>
532
+ <port id="0" precision="I32" />
533
+ </output>
534
+ </layer>
535
+ <layer id="41" name="RaggedToDense_103777" type="RaggedToDense" version="extension">
536
+ <data pad_right="true" />
537
+ <input>
538
+ <port id="0" precision="I32">
539
+ <dim>-1</dim>
540
+ </port>
541
+ <port id="1" precision="I32">
542
+ <dim>-1</dim>
543
+ </port>
544
+ <port id="2" precision="I32">
545
+ <dim>-1</dim>
546
+ </port>
547
+ <port id="3" precision="I32" />
548
+ <port id="4" precision="I32" />
549
+ </input>
550
+ <output>
551
+ <port id="5" precision="I32">
552
+ <dim>-1</dim>
553
+ <dim>-1</dim>
554
+ </port>
555
+ <port id="6" precision="BOOL">
556
+ <dim>-1</dim>
557
+ <dim>-1</dim>
558
+ </port>
559
+ </output>
560
+ </layer>
561
+ <layer id="42" name="Convert_103778" type="Convert" version="opset1">
562
+ <data destination_type="i32" />
563
+ <input>
564
+ <port id="0" precision="BOOL">
565
+ <dim>-1</dim>
566
+ <dim>-1</dim>
567
+ </port>
568
+ </input>
569
+ <output>
570
+ <port id="1" precision="I32">
571
+ <dim>-1</dim>
572
+ <dim>-1</dim>
573
+ </port>
574
+ </output>
575
+ </layer>
576
+ <layer id="43" name="Convert_103778.0" type="Convert" version="opset1">
577
+ <data destination_type="i64" />
578
+ <input>
579
+ <port id="0" precision="I32">
580
+ <dim>-1</dim>
581
+ <dim>-1</dim>
582
+ </port>
583
+ </input>
584
+ <output>
585
+ <port id="1" precision="I64" names="attention_mask">
586
+ <dim>-1</dim>
587
+ <dim>-1</dim>
588
+ </port>
589
+ </output>
590
+ </layer>
591
+ <layer id="45" name="RaggedToDense_103777.0" type="Convert" version="opset1">
592
+ <data destination_type="i64" />
593
+ <input>
594
+ <port id="0" precision="I32">
595
+ <dim>-1</dim>
596
+ <dim>-1</dim>
597
+ </port>
598
+ </input>
599
+ <output>
600
+ <port id="1" precision="I64" names="input_ids">
601
+ <dim>-1</dim>
602
+ <dim>-1</dim>
603
+ </port>
604
+ </output>
605
+ </layer>
606
+ <layer id="46" name="Result_103779" type="Result" version="opset1">
607
+ <input>
608
+ <port id="0" precision="I64">
609
+ <dim>-1</dim>
610
+ <dim>-1</dim>
611
+ </port>
612
+ </input>
613
+ </layer>
614
+ <layer id="44" name="Result_103780" type="Result" version="opset1">
615
+ <input>
616
+ <port id="0" precision="I64">
617
+ <dim>-1</dim>
618
+ <dim>-1</dim>
619
+ </port>
620
+ </input>
621
+ </layer>
622
+ </layers>
623
+ <edges>
624
+ <edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
625
+ <edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
626
+ <edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
627
+ <edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
628
+ <edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
629
+ <edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
630
+ <edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
631
+ <edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
632
+ <edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
633
+ <edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
634
+ <edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
635
+ <edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
636
+ <edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
637
+ <edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
638
+ <edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
639
+ <edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
640
+ <edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
641
+ <edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
642
+ <edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
643
+ <edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
644
+ <edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
645
+ <edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
646
+ <edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
647
+ <edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
648
+ <edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
649
+ <edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
650
+ <edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
651
+ <edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
652
+ <edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
653
+ <edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
654
+ <edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
655
+ <edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
656
+ <edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
657
+ <edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
658
+ <edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
659
+ <edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
660
+ <edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
661
+ <edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
662
+ <edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
663
+ <edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
664
+ <edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
665
+ <edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
666
+ <edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
667
+ <edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
668
+ <edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
669
+ <edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
670
+ <edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
671
+ <edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
672
+ <edge from-layer="32" from-port="19" to-layer="33" to-port="0" />
673
+ <edge from-layer="32" from-port="18" to-layer="33" to-port="1" />
674
+ <edge from-layer="32" from-port="20" to-layer="41" to-port="2" />
675
+ <edge from-layer="32" from-port="18" to-layer="36" to-port="0" />
676
+ <edge from-layer="32" from-port="18" to-layer="41" to-port="0" />
677
+ <edge from-layer="32" from-port="18" to-layer="37" to-port="1" />
678
+ <edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
679
+ <edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
680
+ <edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
681
+ <edge from-layer="36" from-port="2" to-layer="37" to-port="0" />
682
+ <edge from-layer="36" from-port="2" to-layer="41" to-port="1" />
683
+ <edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
684
+ <edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
685
+ <edge from-layer="39" from-port="2" to-layer="41" to-port="3" />
686
+ <edge from-layer="40" from-port="0" to-layer="41" to-port="4" />
687
+ <edge from-layer="41" from-port="6" to-layer="42" to-port="0" />
688
+ <edge from-layer="41" from-port="5" to-layer="45" to-port="0" />
689
+ <edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
690
+ <edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
691
+ <edge from-layer="45" from-port="1" to-layer="46" to-port="0" />
692
+ </edges>
693
+ <rt_info>
694
+ <add_attention_mask value="True" />
695
+ <add_prefix_space />
696
+ <add_special_tokens value="True" />
697
+ <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 %}" />
698
+ <clean_up_tokenization_spaces />
699
+ <detokenizer_input_type value="i64" />
700
+ <eos_token_id value="151645" />
701
+ <handle_special_tokens_with_re />
702
+ <number_of_inputs value="1" />
703
+ <openvino_tokenizers_version value="2025.0.0.0-471-7f2ac4f9648" />
704
+ <openvino_version value="2025.0.0-17908-513dcc5c7b7-releases/2025/0" />
705
+ <original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
706
+ <pad_token_id value="151643" />
707
+ <sentencepiece_version value="0.2.0" />
708
+ <skip_special_tokens value="True" />
709
+ <streaming_detokenizer value="False" />
710
+ <tiktoken_version value="0.7.0" />
711
+ <tokenizer_output_type value="i64" />
712
+ <tokenizers_version value="0.21.0" />
713
+ <transformers_version value="4.47.0" />
714
+ <use_max_padding value="False" />
715
+ <use_sentencepiece_backend value="False" />
716
+ <utf8_replace_mode value="replace" />
717
+ <with_detokenizer value="True" />
718
+ </rt_info>
719
+ </net>
openvino_vision_embeddings_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf474dcc8207ab1d4e55ce8f237eeef90c349fcc4cbf705dc27c412367ea2d08
3
+ size 616892318
openvino_vision_embeddings_model.xml ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 448,
4
+ "width": 448
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.485,
13
+ 0.456,
14
+ 0.406
15
+ ],
16
+ "image_processor_type": "CLIPFeatureExtractor",
17
+ "image_std": [
18
+ 0.229,
19
+ 0.224,
20
+ 0.225
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 448
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<img>",
6
+ "</img>",
7
+ "<IMG_CONTEXT>",
8
+ "<quad>",
9
+ "</quad>",
10
+ "<ref>",
11
+ "</ref>",
12
+ "<box>",
13
+ "</box>"
14
+ ],
15
+ "eos_token": {
16
+ "content": "<|im_end|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a3df087afa0c8890b416fe2c4f3f2593f06181adda4aacf93db8eb34cf0208
3
+ size 11414752
tokenizer_config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_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": "<img>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "</img>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<IMG_CONTEXT>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<quad>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "</quad>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<ref>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "</ref>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<box>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "</box>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "<|im_start|>",
104
+ "<|im_end|>",
105
+ "<img>",
106
+ "</img>",
107
+ "<IMG_CONTEXT>",
108
+ "<quad>",
109
+ "</quad>",
110
+ "<ref>",
111
+ "</ref>",
112
+ "<box>",
113
+ "</box>"
114
+ ],
115
+ "bos_token": null,
116
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
117
+ "clean_up_tokenization_spaces": false,
118
+ "eos_token": "<|im_end|>",
119
+ "errors": "replace",
120
+ "extra_special_tokens": {},
121
+ "model_max_length": 8192,
122
+ "pad_token": "<|endoftext|>",
123
+ "split_special_tokens": false,
124
+ "tokenizer_class": "Qwen2Tokenizer",
125
+ "unk_token": null
126
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff