Upload 23 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,33 @@
+{
+  "</box>": 151673,
+  "</img>": 151666,
+  "</quad>": 151669,
+  "</ref>": 151671,
+  "</tool_call>": 151658,
+  "<IMG_CONTEXT>": 151667,
+  "<box>": 151672,
+  "<img>": 151665,
+  "<quad>": 151668,
+  "<ref>": 151670,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,109 @@
+{
+  "architectures": [
+    "InternVLChatModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
+    "AutoModel": "OpenGVLab/InternVL3-2B--modeling_internvl_chat.InternVLChatModel",
+    "AutoModelForCausalLM": "OpenGVLab/InternVL3-2B--modeling_internvl_chat.InternVLChatModel"
+  },
+  "downsample_ratio": 0.5,
+  "dynamic_image_size": true,
+  "force_image_size": 448,
+  "hidden_size": 1536,
+  "image_fold": null,
+  "img_context_token_id": 151667,
+  "llm_config": {
+    "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "moe_config": null,
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "factor": 2.0,
+      "rope_type": "dynamic",
+      "type": "dynamic"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": true,
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151674
+  },
+  "max_dynamic_patch": 12,
+  "min_dynamic_patch": 1,
+  "model_type": "internvl_chat",
+  "pad2square": false,
+  "ps_version": "v2",
+  "select_layer": -1,
+  "system_message": null,
+  "template": "internvl2_5",
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_backbone_lora": 0,
+  "use_llm_lora": 0,
+  "use_thumbnail": true,
+  "vision_config": {
+    "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
+    "architectures": [
+      "InternVisionModel"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
+      "AutoModel": "modeling_intern_vit.InternVisionModel"
+    },
+    "capacity_factor": 1.2,
+    "drop_path_rate": 0.1,
+    "dropout": 0.0,
+    "eval_capacity_factor": 1.4,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "image_size": 448,
+    "initializer_factor": 0.1,
+    "initializer_range": 1e-10,
+    "intermediate_size": 4096,
+    "laux_allreduce": "all_nodes",
+    "layer_norm_eps": 1e-06,
+    "model_type": "intern_vit_6b",
+    "moe_coeff_ratio": 0.5,
+    "moe_intermediate_size": 768,
+    "moe_output_scale": 4.0,
+    "noisy_gate_policy": "RSample_before",
+    "norm_type": "layer_norm",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_experts": 8,
+    "num_hidden_layers": 24,
+    "num_routed_experts": 4,
+    "num_shared_experts": 4,
+    "patch_size": 14,
+    "qk_normalization": false,
+    "qkv_bias": true,
+    "shared_expert_intermediate_size": 3072,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": true,
+    "use_flash_attn": true,
+    "use_moe": false,
+    "use_residual": true,
+    "use_rts": false,
+    "use_weighted_residual": false
+  }
+}

configuration_intern_vit.py

@@ -0,0 +1,120 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2024 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import os
+from typing import Union
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class InternVisionConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
+    instantiate a vision encoder according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        num_channels (`int`, *optional*, defaults to 3):
+            Number of color channels in the input images (e.g., 3 for RGB).
+        patch_size (`int`, *optional*, defaults to 14):
+            The size (resolution) of each patch.
+        image_size (`int`, *optional*, defaults to 224):
+            The size (resolution) of each image.
+        qkv_bias (`bool`, *optional*, defaults to `False`):
+            Whether to add a bias to the queries and values in the self-attention layers.
+        hidden_size (`int`, *optional*, defaults to 3200):
+            Dimensionality of the encoder layers and the pooler layer.
+        num_attention_heads (`int`, *optional*, defaults to 25):
+            Number of attention heads for each attention layer in the Transformer encoder.
+        intermediate_size (`int`, *optional*, defaults to 12800):
+            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
+        qk_normalization (`bool`, *optional*, defaults to `True`):
+            Whether to normalize the queries and keys in the self-attention layers.
+        num_hidden_layers (`int`, *optional*, defaults to 48):
+            Number of hidden layers in the Transformer encoder.
+        use_flash_attn (`bool`, *optional*, defaults to `True`):
+            Whether to use flash attention mechanism.
+        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
+            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
+            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
+        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
+            The epsilon used by the layer normalization layers.
+        dropout (`float`, *optional*, defaults to 0.0):
+            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
+        drop_path_rate (`float`, *optional*, defaults to 0.0):
+            Dropout rate for stochastic depth.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        initializer_range (`float`, *optional*, defaults to 0.02):
+            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
+        initializer_factor (`float`, *optional*, defaults to 0.1):
+            A factor for layer scale.
+    """
+
+    model_type = 'intern_vit_6b'
+
+    def __init__(
+            self,
+            num_channels=3,
+            patch_size=14,
+            image_size=224,
+            qkv_bias=False,
+            hidden_size=3200,
+            num_attention_heads=25,
+            intermediate_size=12800,
+            qk_normalization=True,
+            num_hidden_layers=48,
+            use_flash_attn=True,
+            hidden_act='gelu',
+            norm_type='rms_norm',
+            layer_norm_eps=1e-6,
+            dropout=0.0,
+            drop_path_rate=0.0,
+            attention_dropout=0.0,
+            initializer_range=0.02,
+            initializer_factor=0.1,
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.dropout = dropout
+        self.drop_path_rate = drop_path_rate
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_channels = num_channels
+        self.patch_size = patch_size
+        self.image_size = image_size
+        self.initializer_range = initializer_range
+        self.initializer_factor = initializer_factor
+        self.attention_dropout = attention_dropout
+        self.layer_norm_eps = layer_norm_eps
+        self.hidden_act = hidden_act
+        self.norm_type = norm_type
+        self.qkv_bias = qkv_bias
+        self.qk_normalization = qk_normalization
+        self.use_flash_attn = use_flash_attn
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
+        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
+
+        if 'vision_config' in config_dict:
+            config_dict = config_dict['vision_config']
+
+        if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
+            logger.warning(
+                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
+                f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
+            )
+
+        return cls.from_dict(config_dict, **kwargs)

configuration_internvl_chat.py

@@ -0,0 +1,97 @@
+# --------------------------------------------------------
+# InternVL
+# Copyright (c) 2024 OpenGVLab
+# Licensed under The MIT License [see LICENSE for details]
+# --------------------------------------------------------
+
+import copy
+
+from transformers import AutoConfig, LlamaConfig, Qwen2Config
+from transformers.configuration_utils import PretrainedConfig
+from transformers.utils import logging
+
+from .configuration_intern_vit import InternVisionConfig
+
+logger = logging.get_logger(__name__)
+
+
+class InternVLChatConfig(PretrainedConfig):
+    model_type = 'internvl_chat'
+    is_composition = True
+
+    def __init__(
+            self,
+            vision_config=None,
+            llm_config=None,
+            use_backbone_lora=0,
+            use_llm_lora=0,
+            select_layer=-1,
+            force_image_size=None,
+            downsample_ratio=0.5,
+            template=None,
+            dynamic_image_size=False,
+            use_thumbnail=False,
+            ps_version='v1',
+            min_dynamic_patch=1,
+            max_dynamic_patch=6,
+            **kwargs):
+        super().__init__(**kwargs)
+
+        if vision_config is None:
+            vision_config = {'architectures': ['InternVisionModel']}
+            logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
+
+        if llm_config is None:
+            llm_config = {'architectures': ['Qwen2ForCausalLM']}
+            logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
+
+        self.vision_config = InternVisionConfig(**vision_config)
+        if llm_config.get('architectures')[0] == 'LlamaForCausalLM':
+            self.llm_config = LlamaConfig(**llm_config)
+        elif llm_config.get('architectures')[0] == 'Qwen2ForCausalLM':
+            self.llm_config = Qwen2Config(**llm_config)
+        else:
+            raise ValueError('Unsupported architecture: {}'.format(llm_config.get('architectures')[0]))
+        self.use_backbone_lora = use_backbone_lora
+        self.use_llm_lora = use_llm_lora
+        self.select_layer = select_layer
+        self.force_image_size = force_image_size
+        self.downsample_ratio = downsample_ratio
+        self.template = template
+        self.dynamic_image_size = dynamic_image_size
+        self.use_thumbnail = use_thumbnail
+        self.ps_version = ps_version  # pixel shuffle version
+        self.min_dynamic_patch = min_dynamic_patch
+        self.max_dynamic_patch = max_dynamic_patch
+        # By default, we use tie_word_embeddings=False for models of all sizes.
+        self.tie_word_embeddings = self.llm_config.tie_word_embeddings
+
+        logger.info(f'vision_select_layer: {self.select_layer}')
+        logger.info(f'ps_version: {self.ps_version}')
+        logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
+        logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
+
+    def to_dict(self):
+        """
+        Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
+
+        Returns:
+            `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
+        """
+        output = copy.deepcopy(self.__dict__)
+        output['vision_config'] = self.vision_config.to_dict()
+        output['llm_config'] = self.llm_config.to_dict()
+        output['model_type'] = self.__class__.model_type
+        output['use_backbone_lora'] = self.use_backbone_lora
+        output['use_llm_lora'] = self.use_llm_lora
+        output['select_layer'] = self.select_layer
+        output['force_image_size'] = self.force_image_size
+        output['downsample_ratio'] = self.downsample_ratio
+        output['template'] = self.template
+        output['dynamic_image_size'] = self.dynamic_image_size
+        output['use_thumbnail'] = self.use_thumbnail
+        output['ps_version'] = self.ps_version
+        output['min_dynamic_patch'] = self.min_dynamic_patch
+        output['max_dynamic_patch'] = self.max_dynamic_patch
+
+        return output

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.52.3"
+}

openvino_config.json

@@ -0,0 +1,27 @@
+{
+  "dtype": "int4",
+  "input_info": null,
+  "optimum_version": "1.25.3",
+  "quantization_config": {
+    "all_layers": null,
+    "backup_precision": null,
+    "bits": 4,
+    "dataset": null,
+    "dtype": "int4",
+    "gptq": null,
+    "group_size": 128,
+    "ignored_scope": null,
+    "lora_correction": null,
+    "num_samples": null,
+    "processor": null,
+    "quant_method": "default",
+    "ratio": 1.0,
+    "scale_estimation": null,
+    "sensitivity_metric": null,
+    "sym": false,
+    "tokenizer": null,
+    "trust_remote_code": false
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.52.3"
+}

openvino_detokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a0d75ca233db27305df00cf870e8cf0e06c6b391d5f22ea0cc5f7afeab38fe
+size 2189806

openvino_detokenizer.xml

@@ -0,0 +1,220 @@
+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_1631039" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_1631039">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Convert_1631209" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Constant_1631041" type="Const" version="opset1">
+			<data element_type="i32" shape="151674" offset="0" size="606696" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151674</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_1631043" type="Const" version="opset1">
+			<data element_type="i32" shape="151674" offset="606696" size="606696" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151674</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_1631045" type="Const" version="opset1">
+			<data element_type="u8" shape="976322" offset="1213392" size="976322" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976322</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Slice_1631050" type="Const" version="opset1">
+			<data element_type="i32" shape="23" offset="2189714" size="92" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>23</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="VocabDecoder_1631052" type="VocabDecoder" version="extension">
+			<data skip_tokens="" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>151674</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>151674</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>976322</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>23</dim>
+				</port>
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="FuzeRagged_1631053" type="FuzeRagged" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="UTF8Validate_1631054" type="UTF8Validate" version="extension">
+			<data replace_mode="true" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="StringTensorPack_1631055" type="StringTensorPack" version="opset15">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="STRING" names="Result_1631056,string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Result_1631056" type="Result" version="opset1" output_names="Result_1631056,string_output">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
+		<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
+		<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
+		<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
+		<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
+		<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
+		<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
+		<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+		<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
+		<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
+		<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<chat_template value="{%- if tools %}&#10;    {{- '&lt;|im_start|>system\n' }}&#10;    {%- if messages[0]['role'] == 'system' %}&#10;        {{- messages[0]['content'] }}&#10;    {%- else %}&#10;        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}&#10;    {%- endif %}&#10;    {{- &quot;\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10;    {%- for tool in tools %}&#10;        {{- &quot;\n&quot; }}&#10;        {{- tool | tojson }}&#10;    {%- endfor %}&#10;    {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10;    {%- if messages[0]['role'] == 'system' %}&#10;        {{- '&lt;|im_start|>system\n' + messages[0]['content'] + '&lt;|im_end|>\n' }}&#10;    {%- else %}&#10;        {{- '&lt;|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.&lt;|im_end|>\n' }}&#10;    {%- endif %}&#10;{%- endif %}&#10;{%- for message in messages %}&#10;    {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) or (message.role == &quot;assistant&quot; and not message.tool_calls) %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + message.content + '&lt;|im_end|>' + '\n' }}&#10;    {%- elif message.role == &quot;assistant&quot; %}&#10;        {{- '&lt;|im_start|>' + message.role }}&#10;        {%- if message.content %}&#10;            {{- '\n' + message.content }}&#10;        {%- endif %}&#10;        {%- for tool_call in message.tool_calls %}&#10;            {%- if tool_call.function is defined %}&#10;                {%- set tool_call = tool_call.function %}&#10;            {%- endif %}&#10;            {{- '\n&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10;            {{- tool_call.name }}&#10;            {{- '&quot;, &quot;arguments&quot;: ' }}&#10;            {{- tool_call.arguments | tojson }}&#10;            {{- '}\n&lt;/tool_call>' }}&#10;        {%- endfor %}&#10;        {{- '&lt;|im_end|>\n' }}&#10;    {%- elif message.role == &quot;tool&quot; %}&#10;        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_start|>user' }}&#10;        {%- endif %}&#10;        {{- '\n&lt;tool_response>\n' }}&#10;        {{- message.content }}&#10;        {{- '\n&lt;/tool_response>' }}&#10;        {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_end|>\n' }}&#10;        {%- endif %}&#10;    {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10;    {{- '&lt;|im_start|>assistant\n' }}&#10;{%- endif %}&#10;" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151645" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
+		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<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}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<sentencepiece_version value="0.2.0" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tiktoken_version value="0.9.0" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.1" />
+		<transformers_version value="4.52.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_language_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a63f29f2125e45a9b6c816773067d417496884176e0460766020d1644d30d9b
+size 914579394

openvino_text_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c018fddd902ef9763b660558c104cfed02596a34e3f5301673b62e889fc5048
+size 233274616

openvino_text_embeddings_model.xml

@@ -0,0 +1,177 @@
+<?xml version="1.0"?>
+<net name="Model3" version="11">
+	<layers>
+		<layer id="0" name="input" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="input">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="self.weight" type="Const" version="opset1">
+			<data element_type="i8" shape="151674, 1536" offset="0" size="232971264" />
+			<output>
+				<port id="0" precision="I8">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Convert_1145818" type="Convert" version="opset1">
+			<data destination_type="f16" />
+			<input>
+				<port id="0" precision="I8">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP16">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="self.weight/scale" type="Const" version="opset1">
+			<data element_type="f16" shape="151674, 1" offset="232971264" size="303348" />
+			<output>
+				<port id="0" precision="FP16">
+					<dim>151674</dim>
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="self.weight/fq_weights_0" type="Multiply" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="FP16">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="FP16">
+					<dim>151674</dim>
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="FP16">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="ov_ext::embedding/Convert" type="Convert" version="opset1">
+			<data destination_type="f32" />
+			<rt_info>
+				<attribute name="decompression" version="0" />
+			</rt_info>
+			<input>
+				<port id="0" precision="FP16">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="FP32">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="ov_ext::embedding/Convert_1" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="ov_ext::embedding/Constant" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="233274612" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="8" name="ov_ext::embedding/Gather" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="FP32">
+					<dim>151674</dim>
+					<dim>1536</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="FP32" names="inputs_embeds">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Result_21649" type="Result" version="opset1" output_names="inputs_embeds">
+			<input>
+				<port id="0" precision="FP32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+					<dim>1536</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="6" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="4" to-port="0" />
+		<edge from-layer="3" from-port="0" to-layer="4" to-port="1" />
+		<edge from-layer="4" from-port="2" to-layer="5" to-port="0" />
+		<edge from-layer="5" from-port="1" to-layer="8" to-port="0" />
+		<edge from-layer="6" from-port="1" to-layer="8" to-port="1" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+	</edges>
+	<rt_info>
+		<Runtime_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<conversion_parameters>
+			<framework value="pytorch" />
+			<is_python_object value="True" />
+		</conversion_parameters>
+		<nncf>
+			<friendly_names_were_updated value="True" />
+			<weight_compression>
+				<advanced_parameters value="{'statistics_path': None, 'awq_params': {'subset_size': 32, 'percent_to_apply': 0.002, 'alpha_min': 0.0, 'alpha_max': 1.0, 'steps': 100}, 'scale_estimation_params': {'subset_size': 64, 'initial_steps': 5, 'scale_steps': 5, 'weight_penalty': -1.0}, 'gptq_params': {'damp_percent': 0.1, 'block_size': 128, 'subset_size': 128}, 'lora_correction_params': {'adapter_rank': 8, 'num_iterations': 3, 'apply_regularization': True, 'subset_size': 128, 'use_int8_adapters': True}}" />
+				<all_layers value="False" />
+				<awq value="False" />
+				<backup_mode value="int8_asym" />
+				<gptq value="False" />
+				<group_size value="-1" />
+				<ignored_scope value="[]" />
+				<lora_correction value="False" />
+				<mode value="int8_sym" />
+				<ratio value="1.0" />
+				<scale_estimation value="False" />
+				<sensitivity_metric value="weight_quantization_error" />
+			</weight_compression>
+		</nncf>
+		<optimum>
+			<nncf_version value="2.15.0" />
+			<optimum_intel_version value="1.24.0.dev0+dba7dce" />
+			<optimum_version value="1.25.3" />
+			<pytorch_version value="2.6.0" />
+			<transformers_version value="4.52.3" />
+		</optimum>
+	</rt_info>
+</net>

openvino_tokenizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5365a0a3c9f496090c293249d6b76fac76f52910e7d2dbbccc3393aea97c1467
+size 5589034

openvino_tokenizer.xml

@@ -0,0 +1,721 @@
+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_1630920" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="Parameter_1630920">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_1630926" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="2" name="StringTensorUnpack_1630921" type="StringTensorUnpack" version="opset15">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="ShapeOf_1630922" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_1630923" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="5" name="Constant_1630924" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="0" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="6" name="Gather_1630925" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I64" />
+			</output>
+		</layer>
+		<layer id="7" name="Constant_1630927" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="8" name="Range_1630928" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Constant_1630929" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="10" name="Constant_1630930" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="11" name="Add_1630931" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" />
+			</output>
+		</layer>
+		<layer id="12" name="Constant_1630932" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="13" name="Range_1630933" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I64" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Constant_1630995" type="Const" version="opset1">
+			<data element_type="u8" shape="552" offset="16" size="552" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>552</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="SpecialTokensSplit_1630996" type="SpecialTokensSplit" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>552</dim>
+				</port>
+			</input>
+			<output>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="CharsMapNormalization_1630997" type="CharsMapNormalization" version="extension">
+			<data add_dummy_prefix="false" remove_extra_whitespaces="false" escape_whitespaces="false" normalization_form="nfc" case_fold="false" nmt="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_1630999" type="Const" version="opset1">
+			<data element_type="u8" shape="110" offset="568" size="110" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>110</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="RegexSplit_1631000" type="RegexSplit" version="extension">
+			<data behaviour="isolate" invert="false" max_splits="-1" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>110</dim>
+				</port>
+			</input>
+			<output>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="12" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="Constant_1631002" type="Const" version="opset1">
+			<data element_type="i32" shape="151674" offset="678" size="606696" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151674</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Constant_1631004" type="Const" version="opset1">
+			<data element_type="i32" shape="151674" offset="607374" size="606696" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151674</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="Constant_1631006" type="Const" version="opset1">
+			<data element_type="u8" shape="976322" offset="1214070" size="976322" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976322</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="Constant_1631014" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2190392" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Constant_1631016" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2795940" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_1631018" type="Const" version="opset1">
+			<data element_type="u8" shape="491359" offset="3401488" size="491359" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>491359</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_1631020" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="3892847" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="Constant_1631022" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="4498395" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_1631024" type="Const" version="opset1">
+			<data element_type="u8" shape="484354" offset="5103943" size="484354" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>484354</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="Constant_1631008" type="Const" version="opset1">
+			<data element_type="i32" shape="31" offset="5588297" size="124" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>31</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Constant_1631010" type="Const" version="opset1">
+			<data element_type="i32" shape="31" offset="5588421" size="124" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>31</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_1631012" type="Const" version="opset1">
+			<data element_type="u8" shape="353" offset="5588545" size="353" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>353</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="Constant_1631025" type="Const" version="opset1">
+			<data element_type="i32" shape="31" offset="5588898" size="124" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>31</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="BPETokenizer_1631026" type="BPETokenizer" version="extension">
+			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>151674</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>151674</dim>
+				</port>
+				<port id="7" precision="U8">
+					<dim>976322</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>491359</dim>
+				</port>
+				<port id="11" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="12" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="13" precision="U8">
+					<dim>484354</dim>
+				</port>
+				<port id="14" precision="I32">
+					<dim>31</dim>
+				</port>
+				<port id="15" precision="I32">
+					<dim>31</dim>
+				</port>
+				<port id="16" precision="U8">
+					<dim>353</dim>
+				</port>
+				<port id="17" precision="I32">
+					<dim>31</dim>
+				</port>
+			</input>
+			<output>
+				<port id="18" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="19" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="20" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="Subtract_1631027" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="34" name="Constant_1631028" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5589022" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="35" name="Minimum_1631029" type="Minimum" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Subtract_1631030" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="Subtract_1631031" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="Constant_1631032" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5589026" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="39" name="ReduceMax_1631033" type="ReduceMax" version="opset1">
+			<data keep_dims="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32" />
+			</output>
+		</layer>
+		<layer id="40" name="Constant_1631034" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5589030" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="41" name="RaggedToDense_1631035" type="RaggedToDense" version="extension">
+			<data pad_right="false" m_pad_max_length="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32" />
+				<port id="4" precision="I32" />
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="42" name="Convert_1631036" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="43" name="Convert_1631036.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="attention_mask">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="RaggedToDense_1631035.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="Result_1631037" type="Result" version="opset1" output_names="input_ids">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+		<layer id="44" name="Result_1631038" type="Result" version="opset1" output_names="attention_mask">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
+		<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
+		<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
+		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
+		<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
+		<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
+		<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
+		<edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
+		<edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
+		<edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
+		<edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
+		<edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
+		<edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
+		<edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
+		<edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
+		<edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
+		<edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
+		<edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
+		<edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
+		<edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
+		<edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
+		<edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
+		<edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
+		<edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
+		<edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
+		<edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
+		<edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
+		<edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
+		<edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
+		<edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
+		<edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
+		<edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
+		<edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
+		<edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
+		<edge from-layer="32" from-port="19" to-layer="33" to-port="0" />
+		<edge from-layer="32" from-port="18" to-layer="33" to-port="1" />
+		<edge from-layer="32" from-port="20" to-layer="41" to-port="2" />
+		<edge from-layer="32" from-port="19" to-layer="36" to-port="0" />
+		<edge from-layer="32" from-port="19" to-layer="41" to-port="1" />
+		<edge from-layer="32" from-port="19" to-layer="37" to-port="0" />
+		<edge from-layer="33" from-port="2" to-layer="35" to-port="0" />
+		<edge from-layer="34" from-port="0" to-layer="35" to-port="1" />
+		<edge from-layer="35" from-port="2" to-layer="36" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="37" to-port="1" />
+		<edge from-layer="36" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="37" from-port="2" to-layer="39" to-port="0" />
+		<edge from-layer="38" from-port="0" to-layer="39" to-port="1" />
+		<edge from-layer="39" from-port="2" to-layer="41" to-port="3" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="4" />
+		<edge from-layer="41" from-port="6" to-layer="42" to-port="0" />
+		<edge from-layer="41" from-port="5" to-layer="45" to-port="0" />
+		<edge from-layer="42" from-port="1" to-layer="43" to-port="0" />
+		<edge from-layer="43" from-port="1" to-layer="44" to-port="0" />
+		<edge from-layer="45" from-port="1" to-layer="46" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<chat_template value="{%- if tools %}&#10;    {{- '&lt;|im_start|>system\n' }}&#10;    {%- if messages[0]['role'] == 'system' %}&#10;        {{- messages[0]['content'] }}&#10;    {%- else %}&#10;        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}&#10;    {%- endif %}&#10;    {{- &quot;\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10;    {%- for tool in tools %}&#10;        {{- &quot;\n&quot; }}&#10;        {{- tool | tojson }}&#10;    {%- endfor %}&#10;    {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10;    {%- if messages[0]['role'] == 'system' %}&#10;        {{- '&lt;|im_start|>system\n' + messages[0]['content'] + '&lt;|im_end|>\n' }}&#10;    {%- else %}&#10;        {{- '&lt;|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.&lt;|im_end|>\n' }}&#10;    {%- endif %}&#10;{%- endif %}&#10;{%- for message in messages %}&#10;    {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) or (message.role == &quot;assistant&quot; and not message.tool_calls) %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + message.content + '&lt;|im_end|>' + '\n' }}&#10;    {%- elif message.role == &quot;assistant&quot; %}&#10;        {{- '&lt;|im_start|>' + message.role }}&#10;        {%- if message.content %}&#10;            {{- '\n' + message.content }}&#10;        {%- endif %}&#10;        {%- for tool_call in message.tool_calls %}&#10;            {%- if tool_call.function is defined %}&#10;                {%- set tool_call = tool_call.function %}&#10;            {%- endif %}&#10;            {{- '\n&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10;            {{- tool_call.name }}&#10;            {{- '&quot;, &quot;arguments&quot;: ' }}&#10;            {{- tool_call.arguments | tojson }}&#10;            {{- '}\n&lt;/tool_call>' }}&#10;        {%- endfor %}&#10;        {{- '&lt;|im_end|>\n' }}&#10;    {%- elif message.role == &quot;tool&quot; %}&#10;        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_start|>user' }}&#10;        {%- endif %}&#10;        {{- '\n&lt;tool_response>\n' }}&#10;        {{- message.content }}&#10;        {{- '\n&lt;/tool_response>' }}&#10;        {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_end|>\n' }}&#10;        {%- endif %}&#10;    {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10;    {{- '&lt;|im_start|>assistant\n' }}&#10;{%- endif %}&#10;" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151645" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2025.1.0.0-523-710ddf14de8" />
+		<openvino_version value="2025.1.0-18503-6fec06580ab-releases/2025/1" />
+		<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}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<sentencepiece_version value="0.2.0" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tiktoken_version value="0.9.0" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.1" />
+		<transformers_version value="4.52.3" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_vision_embeddings_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c691f192dfe3d77922acdd9ef03dfae49bf7efdf9315a4fa00930d1a11b0372
+size 317217188

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 448,
+    "width": 448
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 448
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9ba4b4a6625b5047a1356f6081b641c3e4e6a4a198facbd4bef217747d1685
+size 11423548

tokenizer_config.json

@@ -0,0 +1,280 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151666": {
+      "content": "</img>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151667": {
+      "content": "<IMG_CONTEXT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151668": {
+      "content": "<quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151669": {
+      "content": "</quad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "</ref>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "</box>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12288,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}