初始化项目,由ModelHub XC社区提供模型

Model: maxLWSv2/MotionAtlas-4B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-31 12:38:19 +08:00
commit 306fd2fd2d
13 changed files with 152013 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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

20
README.md Normal file
View File

@@ -0,0 +1,20 @@
---
license: fair-noncommercial-research-license
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- qwen3-vl
- video-language-model
- region-understanding
- motion-captioning
---
# MotionAtlas-4B
This repository contains the MotionAtlas-4B model for **MotionAtlas: Detailed Region Captioning for Motion-Centric Videos**.
**TL; DR:** MotionAtlas shifts motion captioning from global video descriptions to region-aware motion captions, enabling precise evaluation with MotionAtlas-Bench and scalable training with MotionAtlas-Data. The model is designed for detailed motion-centric video understanding over referred regions.
## Usage
For detailed usage of this model, please refer to our [GitHub repo](https://github.com/Kagura-0001/MotionAtlas) and [project page](https://kagura-0001.github.io/projects/MotionAtlas/?v=2).

28
added_tokens.json Normal file
View File

@@ -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
}

120
chat_template.jinja Normal file
View File

@@ -0,0 +1,120 @@
{%- 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' }}
{%- 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' }}
{%- 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 %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"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": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"max_position_embeddings": 262144,
"model_type": "qwen3_vl_text",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"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",
"video_token_id": 151656,
"vision_config": {
"deepstack_visual_indexes": [
5,
11,
17
],
"depth": 24,
"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": 2560,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652
}

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ba9df24d8ef3f0693aaa8608fb996ca53117350f504772b2dcd234222ed4b6e
size 9653631816

39
preprocessor_config.json Normal file
View File

@@ -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": null,
"merge_size": 2,
"min_pixels": null,
"pad_size": null,
"patch_size": 16,
"processor_class": "Qwen3VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_tensors": null,
"size": {
"longest_edge": 16777216,
"shortest_edge": 65536
},
"temporal_patch_size": 2
}

31
special_tokens_map.json Normal file
View File

@@ -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
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

240
tokenizer_config.json Normal file
View File

@@ -0,0 +1,240 @@
{
"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|>",
"processor_class": "Qwen3VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

View File

@@ -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"
}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long