qcf568 commited on
Commit
fc730e5
·
verified ·
1 Parent(s): 4ff3445

Import DanceText/DefakerOne2@master from ModelScope

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ preview/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ release/tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitkeep ADDED
File without changes
README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <h2 align="center">
2
+ Venus-DefakerOne2: A Vision-Forensics Foundation Model<br>
3
+ with Broader Coverage
4
+ </h2>
5
+
6
+ <p align="center">
7
+ <b>GuangJian Team, Ant Group</b><br>
8
+ <b>Technical Committee on Digital Media Forensics and Security, CSIG</b>
9
+ </p>
10
+
11
+ <p align="center">
12
+ <a href="https://arxiv.org/abs/2610.37918"><img src="https://img.shields.io/badge/arXiv-2610.37918-b31b1b?logo=arxiv" alt="arXiv"></a>
13
+ <a href="https://github.com/inclusionAI/DefakerOne2"><img src="https://img.shields.io/badge/GitHub-Code-181717?logo=github" alt="GitHub"></a>
14
+ <a href="https://www.modelscope.cn/models/DanceText/DefakerOne2"><img src="https://img.shields.io/badge/ModelScope-DefakerOne2-624AFF" alt="ModelScope Model"></a>
15
+ <a href="https://www.modelscope.cn/models/DanceText/RRVBench"><img src="https://img.shields.io/badge/ModelScope-RRVBench-624AFF" alt="ModelScope RRVBench"></a>
16
+ <a href="https://venus-guangjian.github.io/Venus-DeFakerOne2/"><img src="https://img.shields.io/badge/Project-Page-success" alt="Project Page"></a>
17
+ </p>
18
+
19
+ ### 1. Environment Requirements
20
+
21
+ Python **3.12.3**
22
+
23
+ ```bash
24
+ pip install torch==2.9.0 torchvision==0.24.0 ms-swift=4.1.0 numpy==1.26.0 scipy==1.11.3 scikit-learn==1.3.2 torchao==0.16.0
25
+ ```
26
+
27
+ ### 2. Model Download
28
+
29
+ ```bash
30
+ modelscope download --model DanceText/DefakerOne2 --local_dir [target_save_path]
31
+ ```
32
+
33
+ Two checkpoints are provided under the download directory:
34
+
35
+ | Directory | Description |
36
+ | --- | --- |
37
+ | `preview/` | **DefakerOne2-preview** — can be used for reproducing the scores reported in the paper. |
38
+ | `release/` | **DefakerOne2-release** — trained with more data; expected to perform better in most cases. |
39
+
40
+ ### 3. Inference Data Format
41
+
42
+ Inference inputs are **JSONL** files, one sample per line.
43
+
44
+ **Image**
45
+
46
+ ```json
47
+ {"messages": [{"role": "user", "content": "<image>Is this image real or fake? Answer only Real or Fake"}], "images": ["your_image_path.jpg"]}
48
+ ```
49
+
50
+ **Video**
51
+
52
+ ```json
53
+ {"messages": [{"role": "user", "content": "<video>Is this video real or fake? Answer only Real or Fake"}], "images": ["your_video_path.mp4"]}
54
+ ```
55
+
56
+ The prompt is fixed and direct, so the model commits to its conclusion in a **single output token** (`Real` / `Fake`).
57
+
58
+ ### 4. Inference Command
59
+
60
+ ```bash
61
+ CUDA_VISIBLE_DEVICES=0 MIN_PIXELS=262144 MAX_PIXELS=2408448 --model [model_weight_dir] --val_dataset [val_dataset_jsonl_path] --result_path [prediction_jsonl_save_path] --max_new_token 16 --enable_thinking False --batch_size 1 --num_workers 8 --logprobs True --top_logprobs 20
62
+ ```
63
+
64
+ ### 5. Citation
65
+ ```
66
+ @misc{qu2026venusdefakerone2visionforensicsfoundationmodel,
67
+ title={Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage},
68
+ author={Chenfan Qu and Yachao Liang and Mingqi Fang and Jiangwei Xie and Zhenming Wang and Baoyue Zhang and Changjiang Jiang and Zheng Chang and Fanli Jin and Xuekang Zhu and Kaiwen Feng and Junchi Li and Weihong Zhang and Haoyue Wang and Chenfeng Zhang and Yinan Xia and Fangming Cui and Dong Fan and Jingjing Liu and Tianyi Zhang and Luobin Chen and Ji-Zhe Zhou and Sheng Li and Wei Wang and Bin Li and Ran He and Xinpeng Zhang and Linna Zhou and Jian Liu and Weiqiang Wang},
69
+ year={2026},
70
+ eprint={2610.37918},
71
+ archivePrefix={arXiv},
72
+ primaryClass={cs.CV},
73
+ url={https://arxiv.org/abs/2610.37918},
74
+ }
75
+ ```
preview/chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is true %}
150
+ {{- '<think>\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n\n</think>\n\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
preview/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "hidden_size": 2048,
7
+ "image_token_id": 248056,
8
+ "model_type": "qwen3_5",
9
+ "text_config": {
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "attn_output_gate": true,
13
+ "bos_token_id": null,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 248044,
16
+ "full_attention_interval": 4,
17
+ "head_dim": 256,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 6144,
22
+ "layer_types": [
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "full_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention"
47
+ ],
48
+ "linear_conv_kernel_dim": 4,
49
+ "linear_key_head_dim": 128,
50
+ "linear_num_key_heads": 16,
51
+ "linear_num_value_heads": 16,
52
+ "linear_value_head_dim": 128,
53
+ "mamba_ssm_dtype": "float32",
54
+ "max_position_embeddings": 262144,
55
+ "mlp_only_layers": [],
56
+ "model_type": "qwen3_5_text",
57
+ "mtp_num_hidden_layers": 1,
58
+ "mtp_use_dedicated_embeddings": false,
59
+ "num_attention_heads": 8,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "pad_token_id": 248044,
63
+ "partial_rotary_factor": 0.25,
64
+ "rms_norm_eps": 1e-06,
65
+ "rope_parameters": {
66
+ "mrope_interleaved": true,
67
+ "mrope_section": [
68
+ 11,
69
+ 11,
70
+ 10
71
+ ],
72
+ "partial_rotary_factor": 0.25,
73
+ "rope_theta": 10000000,
74
+ "rope_type": "default"
75
+ },
76
+ "tie_word_embeddings": true,
77
+ "use_cache": true,
78
+ "vocab_size": 248320
79
+ },
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.2.0",
82
+ "video_token_id": 248057,
83
+ "vision_config": {
84
+ "deepstack_visual_indexes": [],
85
+ "depth": 24,
86
+ "dtype": "bfloat16",
87
+ "hidden_act": "gelu_pytorch_tanh",
88
+ "hidden_size": 1024,
89
+ "in_channels": 3,
90
+ "initializer_range": 0.02,
91
+ "intermediate_size": 4096,
92
+ "model_type": "qwen3_5",
93
+ "num_heads": 16,
94
+ "num_position_embeddings": 2304,
95
+ "out_hidden_size": 2048,
96
+ "patch_size": 16,
97
+ "spatial_merge_size": 2,
98
+ "temporal_patch_size": 2
99
+ },
100
+ "vision_end_token_id": 248054,
101
+ "vision_start_token_id": 248053
102
+ }
preview/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248044,
5
+ 248046
6
+ ],
7
+ "transformers_version": "5.2.0",
8
+ "use_cache": true
9
+ }
preview/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e89b8add074c082746481b080cfd079ff801b826e2397bf96ed6ed0b3ac3b7c
3
+ size 4426558864
preview/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
preview/processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
preview/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
preview/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }
release/.gitkeep ADDED
File without changes
release/chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is true %}
150
+ {{- '<think>\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n\n</think>\n\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
release/config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "hidden_size": 2048,
7
+ "image_token_id": 248056,
8
+ "model_type": "qwen3_5",
9
+ "text_config": {
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "attn_output_gate": true,
13
+ "bos_token_id": null,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 248044,
16
+ "full_attention_interval": 4,
17
+ "head_dim": 256,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 6144,
22
+ "layer_types": [
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "full_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention"
47
+ ],
48
+ "linear_conv_kernel_dim": 4,
49
+ "linear_key_head_dim": 128,
50
+ "linear_num_key_heads": 16,
51
+ "linear_num_value_heads": 16,
52
+ "linear_value_head_dim": 128,
53
+ "mamba_ssm_dtype": "float32",
54
+ "max_position_embeddings": 262144,
55
+ "mlp_only_layers": [],
56
+ "model_type": "qwen3_5_text",
57
+ "mtp_num_hidden_layers": 1,
58
+ "mtp_use_dedicated_embeddings": false,
59
+ "num_attention_heads": 8,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "pad_token_id": 248044,
63
+ "partial_rotary_factor": 0.25,
64
+ "rms_norm_eps": 1e-06,
65
+ "rope_parameters": {
66
+ "mrope_interleaved": true,
67
+ "mrope_section": [
68
+ 11,
69
+ 11,
70
+ 10
71
+ ],
72
+ "partial_rotary_factor": 0.25,
73
+ "rope_theta": 10000000,
74
+ "rope_type": "default"
75
+ },
76
+ "tie_word_embeddings": true,
77
+ "use_cache": true,
78
+ "vocab_size": 248320
79
+ },
80
+ "tie_word_embeddings": true,
81
+ "transformers_version": "5.2.0",
82
+ "video_token_id": 248057,
83
+ "vision_config": {
84
+ "deepstack_visual_indexes": [],
85
+ "depth": 24,
86
+ "dtype": "bfloat16",
87
+ "hidden_act": "gelu_pytorch_tanh",
88
+ "hidden_size": 1024,
89
+ "in_channels": 3,
90
+ "initializer_range": 0.02,
91
+ "intermediate_size": 4096,
92
+ "model_type": "qwen3_5",
93
+ "num_heads": 16,
94
+ "num_position_embeddings": 2304,
95
+ "out_hidden_size": 2048,
96
+ "patch_size": 16,
97
+ "spatial_merge_size": 2,
98
+ "temporal_patch_size": 2
99
+ },
100
+ "vision_end_token_id": 248054,
101
+ "vision_start_token_id": 248053
102
+ }
release/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248044,
5
+ 248046
6
+ ],
7
+ "transformers_version": "5.2.0",
8
+ "use_cache": true
9
+ }
release/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bab60b098f7a6e4e6b85217c9ce571d8912dcb7d8099de2535c90a208eff539
3
+ size 4426558864
release/preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
release/processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
release/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
release/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }