Upload folder using huggingface_hub

.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 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,125 @@
+{%- set default_system_message = 'Represent the user\'s input.' -%}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- else %}
+        {{- default_system_message + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\n' + default_system_message + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 +1,66 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73fa9caeddeb3ff831d46c085a7a5708343248ca777e90f2d486964464509c1
+size 4255140312

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": 1310720,
+  "merge_size": 2,
+  "min_pixels": 4096,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 1310720,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2
+}

scripts/qwen3_vl_embedding.py

@@ -0,0 +1,326 @@
+import torch
+import torch.nn.functional as F
+import unicodedata
+import numpy as np
+import logging
+
+from PIL import Image
+from dataclasses import dataclass
+from typing import Optional, List, Union, Dict, Any
+from transformers.models.qwen3_vl.modeling_qwen3_vl import Qwen3VLPreTrainedModel, Qwen3VLModel, Qwen3VLConfig
+from transformers.models.qwen3_vl.processing_qwen3_vl import Qwen3VLProcessor
+from transformers.modeling_outputs import ModelOutput
+from transformers.processing_utils import Unpack
+from transformers.utils import TransformersKwargs
+from transformers.cache_utils import Cache
+from transformers.utils.generic import check_model_inputs
+from qwen_vl_utils.vision_process import process_vision_info
+
+logger = logging.getLogger(__name__)
+
+# Constants for configuration
+MAX_LENGTH = 8192
+IMAGE_BASE_FACTOR = 16
+IMAGE_FACTOR = IMAGE_BASE_FACTOR * 2
+MIN_PIXELS = 4 * IMAGE_FACTOR * IMAGE_FACTOR
+MAX_PIXELS = 1800 * IMAGE_FACTOR * IMAGE_FACTOR
+FPS = 1
+MAX_FRAMES = 64
+FRAME_MAX_PIXELS = 768 * IMAGE_FACTOR * IMAGE_FACTOR
+MAX_TOTAL_PIXELS = 10 * FRAME_MAX_PIXELS
+PAD_TOKEN = "<|endoftext|>"
+
+# Define output structure for embeddings
+@dataclass
+class Qwen3VLForEmbeddingOutput(ModelOutput):
+    last_hidden_state: Optional[torch.FloatTensor] = None
+    attention_mask: Optional[torch.Tensor] = None
+
+# Define model class to compute embeddings
+class Qwen3VLForEmbedding(Qwen3VLPreTrainedModel):
+    _checkpoint_conversion_mapping = {}
+    accepts_loss_kwargs = False
+    config: Qwen3VLConfig
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.model = Qwen3VLModel(config)
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.model.get_input_embeddings()
+
+    def set_input_embeddings(self, value):
+        self.model.set_input_embeddings(value)
+
+    def set_decoder(self, decoder):
+        self.model.set_decoder(decoder)
+
+    def get_decoder(self):
+        return self.model.get_decoder()
+
+    # Extract video features from model
+    def get_video_features(self, pixel_values_videos: torch.FloatTensor,
+                           video_grid_thw: Optional[torch.LongTensor] = None):
+        return self.model.get_video_features(pixel_values_videos, video_grid_thw)
+
+    # Extract image features from model
+    def get_image_features(self, pixel_values: torch.FloatTensor,
+                           image_grid_thw: Optional[torch.LongTensor] = None):
+        return self.model.get_image_features(pixel_values, image_grid_thw)
+
+    # Make modules accessible through properties
+    @property
+    def language_model(self):
+        return self.model.language_model
+
+    @property
+    def visual(self):
+        return self.model.visual
+
+    # Forward pass through model with input parameters
+    # @check_model_inputs
+    def forward(self,
+                input_ids: torch.LongTensor = None,
+                attention_mask: Optional[torch.Tensor] = None,
+                position_ids: Optional[torch.LongTensor] = None,
+                past_key_values: Optional[Cache] = None,
+                inputs_embeds: Optional[torch.FloatTensor] = None,
+                pixel_values: Optional[torch.Tensor] = None,
+                pixel_values_videos: Optional[torch.FloatTensor] = None,
+                image_grid_thw: Optional[torch.LongTensor] = None,
+                video_grid_thw: Optional[torch.LongTensor] = None,
+                cache_position: Optional[torch.LongTensor] = None,
+                logits_to_keep: Union[int, torch.Tensor] = 0,
+                **kwargs: Unpack[TransformersKwargs],
+    ) -> Union[tuple, Qwen3VLForEmbeddingOutput]:
+        # Pass inputs through the model
+        outputs = self.model(
+            input_ids=input_ids,
+            pixel_values=pixel_values,
+            pixel_values_videos=pixel_values_videos,
+            image_grid_thw=image_grid_thw,
+            video_grid_thw=video_grid_thw,
+            position_ids=position_ids,
+            attention_mask=attention_mask,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            cache_position=cache_position,
+            **kwargs,
+        )
+        # Return the model output
+        return Qwen3VLForEmbeddingOutput(
+            last_hidden_state=outputs.last_hidden_state,
+            attention_mask=attention_mask,
+        )
+
+# Define embedder class for processing inputs and generating embeddings
+class Qwen3VLEmbedder():
+    def __init__(self, model_name_or_path: str, max_length: int = MAX_LENGTH,
+                 instruction: Optional[str] = None, **kwargs):
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.max_length = max_length
+        self.instruction = instruction or "Represent the user's input."
+        # Set pixel and frame configurations
+        self.min_pixels = kwargs.pop('min_pixels', MIN_PIXELS)
+        self.max_pixels = kwargs.pop('max_pixels', MAX_PIXELS)
+        self.total_pixels = kwargs.pop('total_pixels', MAX_TOTAL_PIXELS)
+        self.fps = kwargs.pop('fps', FPS)
+        self.num_frames = kwargs.pop('num_frames', MAX_FRAMES)
+        self.max_frames = kwargs.pop('max_frames', MAX_FRAMES)
+
+        # Initialize model and processor
+        self.model = Qwen3VLForEmbedding.from_pretrained(
+            model_name_or_path, trust_remote_code=True, **kwargs
+        ).to(device)
+        self.processor = Qwen3VLProcessor.from_pretrained(
+            model_name_or_path, padding_side='right'
+        )
+
+        # Define padding token id
+        self.model.eval()  # Set model to evaluation mode
+
+    # Forward pass for the embedder model
+    @torch.no_grad()
+    def forward(self, inputs: Dict[str, Any]) -> Dict[str, torch.Tensor]:
+        outputs = self.model(**inputs)
+        return {
+            'last_hidden_state': outputs.last_hidden_state,
+            'attention_mask': inputs.get('attention_mask')
+        }
+
+    # Sample frames from video files
+    def _sample_frames(self, frames: List[str], num_segments: int, max_segments: int) -> List[str]:
+        duration = len(frames)
+        frame_id_array = np.linspace(0, duration - 1, num_segments, dtype=int)
+        frame_id_list = frame_id_array.tolist()
+        last_frame_id = frame_id_list[-1]
+
+        # Create a list of sampled frames
+        sampled_frames = []
+        for frame_idx in frame_id_list:
+            try:
+                sampled_frames.append(frames[frame_idx])
+            except:
+                break
+        # Ensure the sampled list meets the required segment count
+        while len(sampled_frames) < num_segments:
+            sampled_frames.append(frames[last_frame_id])
+        return sampled_frames[:max_segments]
+
+    # Truncate token sequence to a specified max length
+    def _truncate_tokens(self, token_ids: List[int], max_length: int) -> List[int]:
+        if len(token_ids) <= max_length:
+            return token_ids
+
+        special_token_ids = set(self.processor.tokenizer.all_special_ids)
+        num_special = sum(1 for token_idx in token_ids if token_idx in special_token_ids)
+        num_non_special_to_keep = max_length - num_special
+
+        final_token_ids = []
+        non_special_kept_count = 0
+        # Ensure retention of special tokens while truncating the rest
+        for token_idx in token_ids:
+            if token_idx in special_token_ids:
+                final_token_ids.append(token_idx)
+            elif non_special_kept_count < num_non_special_to_keep:
+                final_token_ids.append(token_idx)
+                non_special_kept_count += 1
+        return final_token_ids
+
+    # Format input based on provided text, image, video, and instruction
+    def format_model_input(self, text: Optional[str] = None,
+                           image: Optional[Union[str, Image.Image]] = None,
+                           video: Optional[Union[str, List[str]]] = None,
+                           instruction: Optional[str] = None,
+                           fps: Optional[float] = None,
+                           max_frames: Optional[int] = None) -> List[Dict]:
+
+        # Ensure instruction ends with punctuation
+        if instruction:
+            instruction = instruction.strip()
+            if instruction and not unicodedata.category(instruction[-1]).startswith('P'):
+                instruction = instruction + '.'
+
+        # Initialize conversation with system prompts
+        content = []
+        conversation = [
+            {"role": "system", "content": [{"type": "text", "text": instruction or self.instruction}]},
+            {"role": "user", "content": content}
+        ]
+
+        # Add text, image, or video content to conversation
+        if not text and not image and not video:
+            content.append({'type': 'text', 'text': ""})
+            return conversation
+
+        if video:
+            video_content = None
+            if isinstance(video, list):
+                video_content = video
+                if self.num_frames is not None or self.max_frames is not None:
+                    video_content = self._sample_frames(video_content, self.num_frames, self.max_frames)
+                video_content = ['file://' + ele for ele in video_content]
+            elif isinstance(video, str):
+                video_content = video if video.startswith(('http', 'oss')) else 'file://' + video
+            else:
+                video_content = video
+
+            # Add video input details to content
+            if video_content:
+                content.append({
+                    'type': 'video', 'video': video_content,
+                    'total_pixels': self.total_pixels,
+                    'max_frames': max_frames or self.max_frames,
+                    'fps': fps or self.fps,
+                    'sample_fps': fps or self.fps,
+                })
+
+        if image:
+            image_content = None
+            if isinstance(image, Image.Image):
+                image_content = image
+            elif isinstance(image, str):
+                image_content = image if image.startswith(('http', 'oss')) else 'file://' + image
+            else:
+                image_content = image
+
+            # Add image input details to content
+            if image_content:
+                content.append({
+                    'type': 'image', 'image': image_content,
+                    "min_pixels": self.min_pixels,
+                    "max_pixels": self.max_pixels
+                })
+
+        if text:
+            content.append({'type': 'text', 'text': text})
+
+        return conversation
+
+    # Preprocess input conversations for model consumption
+    def _preprocess_inputs(self, conversations: List[List[Dict]]) -> Dict[str, torch.Tensor]:
+        text = self.processor.apply_chat_template(
+            conversations, add_generation_prompt=True, tokenize=False
+        )
+
+        try:
+            images, video_inputs, video_kwargs = process_vision_info(
+                conversations, image_patch_size=16,
+                return_video_metadata=True, return_video_kwargs=True
+            )
+        except Exception as e:
+            logger.warning(f"Error in processing vision info: {e}")
+            images = None
+            video_inputs = None
+            video_kwargs = {'do_sample_frames': False}
+            text = self.processor.apply_chat_template(
+                [{'role': 'user', 'content': [{'type': 'text', 'text': 'NULL'}]}], 
+                add_generation_prompt=True, tokenize=False
+            )
+
+        if video_inputs is not None:
+            videos, video_metadata = zip(*video_inputs)
+            videos = list(videos)
+            video_metadata = list(video_metadata)
+        else:
+            videos, video_metadata = None, None
+
+        inputs = self.processor(
+            text=text, images=images, videos=videos, video_metadata=video_metadata, truncation=True, 
+            max_length=self.max_length, padding=True, do_resize=False, return_tensors='pt',
+            **video_kwargs
+        )
+        return inputs
+
+    # Pool the last hidden state by attention mask for embeddings
+    @staticmethod
+    def _pooling_last(hidden_state: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
+        flipped_tensor = attention_mask.flip(dims=[1])
+        last_one_positions = flipped_tensor.argmax(dim=1)
+        col = attention_mask.shape[1] - last_one_positions - 1
+        row = torch.arange(hidden_state.shape[0], device=hidden_state.device)
+        return hidden_state[row, col]
+
+    # Process inputs to generate normalized embeddings
+    def process(self, inputs: List[Dict[str, Any]], normalize: bool = True) -> tuple:
+        conversations = [self.format_model_input(
+            text=ele.get('text'),
+            image=ele.get('image'),
+            video=ele.get('video'),
+            instruction=ele.get('instruction'),
+            fps=ele.get('fps'),
+            max_frames=ele.get('max_frames')
+        ) for ele in inputs]
+
+        processed_inputs = self._preprocess_inputs(conversations)
+        processed_inputs = {k: v.to(self.model.device) for k, v in processed_inputs.items()}
+
+        outputs = self.forward(processed_inputs)
+        embeddings = self._pooling_last(outputs['last_hidden_state'], outputs['attention_mask'])
+
+        # Normalize the embeddings if specified
+        if normalize:
+            embeddings = F.normalize(embeddings, p=2, dim=-1)
+
+        return embeddings

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:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
+size 11423705

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_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": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}