ScienceOne-AI commited on
Commit
21d27ec
·
verified ·
1 Parent(s): 759d859

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ms_upload_cache ADDED
@@ -0,0 +1 @@
 
 
1
+ {"version": 3, "repo_id": "ScienceOne-AI/S1-Omni-Image", "files": {"added_tokens.json|1780762392.8203733|758": {"hash": "9279fee2046a9099b539fc4c19d84c3bc82655f55e078b9d5a7dc780bbbb870c", "size": 758, "status": "c"}, "generation_config.json|1780762392.8537204|214": {"hash": "6ae7c44dde74623cb7cfd45c1657964e70ab5d791089f0a1c39dc5e6779007cb", "size": 214, "status": "c"}, "chat_template.jinja|1780762392.808113|5199": {"hash": "36e042fe45641f067b1f2381fcc8955d10d956a3ed333ecdf7f7eb0916f68956", "size": 5199, "status": "c"}, "config.json|1780889520.352207|4566": {"hash": "8119c77d69fc199732aae67c3fee7c3f12c6d6b103bf8691eef2a019f9f82dce", "size": 4566, "status": "c"}, "merges.txt|1780762484.3199234|1671853": {"hash": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5", "size": 1671853}}}
added_tokens.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<image_edit>": 151670,
6
+ "<image_gen>": 151669,
7
+ "<think>": 151667,
8
+ "<tool_call>": 151657,
9
+ "<tool_response>": 151665,
10
+ "<|box_end|>": 151649,
11
+ "<|box_start|>": 151648,
12
+ "<|endoftext|>": 151643,
13
+ "<|file_sep|>": 151664,
14
+ "<|fim_middle|>": 151660,
15
+ "<|fim_pad|>": 151662,
16
+ "<|fim_prefix|>": 151659,
17
+ "<|fim_suffix|>": 151661,
18
+ "<|im_end|>": 151645,
19
+ "<|im_start|>": 151644,
20
+ "<|image_pad|>": 151655,
21
+ "<|object_ref_end|>": 151647,
22
+ "<|object_ref_start|>": 151646,
23
+ "<|quad_end|>": 151651,
24
+ "<|quad_start|>": 151650,
25
+ "<|repo_name|>": 151663,
26
+ "<|video_pad|>": 151656,
27
+ "<|vision_end|>": 151653,
28
+ "<|vision_pad|>": 151654,
29
+ "<|vision_start|>": 151652
30
+ }
chat_template.jinja ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- else %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if do_vision_count %}
10
+ {%- set image_count.value = image_count.value + 1 %}
11
+ {%- endif %}
12
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
13
+ <|vision_start|><|image_pad|><|vision_end|>
14
+ {%- elif 'video' in item or item.type == 'video' %}
15
+ {%- if do_vision_count %}
16
+ {%- set video_count.value = video_count.value + 1 %}
17
+ {%- endif %}
18
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
19
+ <|vision_start|><|video_pad|><|vision_end|>
20
+ {%- elif 'text' in item %}
21
+ {{- item.text }}
22
+ {%- endif %}
23
+ {%- endfor %}
24
+ {%- endif %}
25
+ {%- endmacro %}
26
+ {%- if tools %}
27
+ {{- '<|im_start|>system\n' }}
28
+ {%- if messages[0].role == 'system' %}
29
+ {{- render_content(messages[0].content, false) + '\n\n' }}
30
+ {%- endif %}
31
+ {{- "# 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>" }}
32
+ {%- for tool in tools %}
33
+ {{- "\n" }}
34
+ {{- tool | tojson }}
35
+ {%- endfor %}
36
+ {{- "\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" }}
37
+ {%- else %}
38
+ {%- if messages[0].role == 'system' %}
39
+ {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
40
+ {%- endif %}
41
+ {%- endif %}
42
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
43
+ {%- for message in messages[::-1] %}
44
+ {%- set index = (messages|length - 1) - loop.index0 %}
45
+ {%- if ns.multi_step_tool and message.role == "user" %}
46
+ {%- set content = render_content(message.content, false) %}
47
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
48
+ {%- set ns.multi_step_tool = false %}
49
+ {%- set ns.last_query_index = index %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- endfor %}
53
+ {%- for message in messages %}
54
+ {%- set content = render_content(message.content, True) %}
55
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {%- set reasoning_content = '' %}
59
+ {%- if message.reasoning_content is string %}
60
+ {%- set reasoning_content = message.reasoning_content %}
61
+ {%- else %}
62
+ {%- if '</think>' in content %}
63
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
64
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- if loop.index0 > ns.last_query_index %}
68
+ {%- if loop.last or (not loop.last and reasoning_content) %}
69
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
70
+ {%- else %}
71
+ {{- '<|im_start|>' + message.role + '\n' + content }}
72
+ {%- endif %}
73
+ {%- else %}
74
+ {{- '<|im_start|>' + message.role + '\n' + content }}
75
+ {%- endif %}
76
+ {%- if message.tool_calls %}
77
+ {%- for tool_call in message.tool_calls %}
78
+ {%- if (loop.first and content) or (not loop.first) %}
79
+ {{- '\n' }}
80
+ {%- endif %}
81
+ {%- if tool_call.function %}
82
+ {%- set tool_call = tool_call.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>\n{"name": "' }}
85
+ {{- tool_call.name }}
86
+ {{- '", "arguments": ' }}
87
+ {%- if tool_call.arguments is string %}
88
+ {{- tool_call.arguments }}
89
+ {%- else %}
90
+ {{- tool_call.arguments | tojson }}
91
+ {%- endif %}
92
+ {{- '}\n</tool_call>' }}
93
+ {%- endfor %}
94
+ {%- endif %}
95
+ {{- '<|im_end|>\n' }}
96
+ {%- elif message.role == "tool" %}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|im_start|>user' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
104
+ {{- '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- endfor %}
108
+ {%- if add_generation_prompt %}
109
+ {{- '<|im_start|>assistant\n<think>\n' }}
110
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "s1-omni-image-sharded",
3
+ "format_version": 1,
4
+ "architectures": [
5
+ "S1OmniImageModel"
6
+ ],
7
+ "prefixes": {
8
+ "qwen3_vl": "qwen3_vl.",
9
+ "alignment_mlp": "alignment_mlp.",
10
+ "dit": "dit.",
11
+ "vae": "vae."
12
+ },
13
+ "qwen3_vl_config": {
14
+ "architectures": [
15
+ "Qwen3VLForConditionalGeneration"
16
+ ],
17
+ "dtype": "bfloat16",
18
+ "eos_token_id": 151645,
19
+ "hidden_size": 5120,
20
+ "image_token_id": 151655,
21
+ "model_type": "qwen3_vl",
22
+ "pad_token_id": 151643,
23
+ "text_config": {
24
+ "attention_bias": false,
25
+ "attention_dropout": 0.0,
26
+ "bos_token_id": 151643,
27
+ "dtype": "bfloat16",
28
+ "eos_token_id": 151645,
29
+ "head_dim": 128,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 5120,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 25600,
34
+ "max_position_embeddings": 262144,
35
+ "model_type": "qwen3_vl_text",
36
+ "num_attention_heads": 64,
37
+ "num_hidden_layers": 64,
38
+ "num_key_value_heads": 8,
39
+ "pad_token_id": 151643,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "mrope_interleaved": true,
43
+ "mrope_section": [
44
+ 24,
45
+ 20,
46
+ 20
47
+ ],
48
+ "rope_type": "default"
49
+ },
50
+ "rope_theta": 5000000,
51
+ "use_cache": false,
52
+ "vocab_size": 151936
53
+ },
54
+ "tie_word_embeddings": false,
55
+ "transformers_version": "4.57.6",
56
+ "video_token_id": 151656,
57
+ "vision_config": {
58
+ "deepstack_visual_indexes": [
59
+ 8,
60
+ 16,
61
+ 24
62
+ ],
63
+ "depth": 27,
64
+ "dtype": "bfloat16",
65
+ "hidden_act": "gelu_pytorch_tanh",
66
+ "hidden_size": 1152,
67
+ "in_channels": 3,
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 4304,
70
+ "model_type": "qwen3_vl",
71
+ "num_heads": 16,
72
+ "num_position_embeddings": 2304,
73
+ "out_hidden_size": 5120,
74
+ "pad_token_id": 151643,
75
+ "patch_size": 16,
76
+ "spatial_merge_size": 2,
77
+ "temporal_patch_size": 2
78
+ },
79
+ "vision_end_token_id": 151653,
80
+ "vision_start_token_id": 151652
81
+ },
82
+ "transformer_config": {
83
+ "_class_name": "QwenImageTransformer2DModel",
84
+ "_diffusers_version": "0.36.0.dev0",
85
+ "attention_head_dim": 128,
86
+ "axes_dims_rope": [
87
+ 16,
88
+ 56,
89
+ 56
90
+ ],
91
+ "guidance_embeds": false,
92
+ "in_channels": 64,
93
+ "joint_attention_dim": 3584,
94
+ "num_attention_heads": 24,
95
+ "num_layers": 60,
96
+ "out_channels": 16,
97
+ "patch_size": 2,
98
+ "zero_cond_t": true
99
+ },
100
+ "vae_config": {
101
+ "_class_name": "AutoencoderKLQwenImage",
102
+ "_diffusers_version": "0.36.0.dev0",
103
+ "attn_scales": [],
104
+ "base_dim": 96,
105
+ "dim_mult": [
106
+ 1,
107
+ 2,
108
+ 4,
109
+ 4
110
+ ],
111
+ "dropout": 0.0,
112
+ "latents_mean": [
113
+ -0.7571,
114
+ -0.7089,
115
+ -0.9113,
116
+ 0.1075,
117
+ -0.1745,
118
+ 0.9653,
119
+ -0.1517,
120
+ 1.5508,
121
+ 0.4134,
122
+ -0.0715,
123
+ 0.5517,
124
+ -0.3632,
125
+ -0.1922,
126
+ -0.9497,
127
+ 0.2503,
128
+ -0.2921
129
+ ],
130
+ "latents_std": [
131
+ 2.8184,
132
+ 1.4541,
133
+ 2.3275,
134
+ 2.6558,
135
+ 1.2196,
136
+ 1.7708,
137
+ 2.6052,
138
+ 2.0743,
139
+ 3.2687,
140
+ 2.1526,
141
+ 2.8652,
142
+ 1.5579,
143
+ 1.6382,
144
+ 1.1253,
145
+ 2.8251,
146
+ 1.916
147
+ ],
148
+ "num_res_blocks": 2,
149
+ "temperal_downsample": [
150
+ false,
151
+ true,
152
+ true
153
+ ],
154
+ "z_dim": 16
155
+ },
156
+ "scheduler_config": {
157
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
158
+ "_diffusers_version": "0.36.0.dev0",
159
+ "base_image_seq_len": 256,
160
+ "base_shift": 0.5,
161
+ "invert_sigmas": false,
162
+ "max_image_seq_len": 8192,
163
+ "max_shift": 0.9,
164
+ "num_train_timesteps": 1000,
165
+ "shift": 1.0,
166
+ "shift_terminal": 0.02,
167
+ "stochastic_sampling": false,
168
+ "time_shift_type": "exponential",
169
+ "use_beta_sigmas": false,
170
+ "use_dynamic_shifting": true,
171
+ "use_exponential_sigmas": false,
172
+ "use_karras_sigmas": false
173
+ },
174
+ "alignment_mlp": {
175
+ "type": "mlp",
176
+ "input_dim": 5120,
177
+ "hidden_dim": 5120,
178
+ "output_dim": 3584
179
+ },
180
+ "special_tokens": {
181
+ "think_start": "<think>",
182
+ "think_end": "</think>",
183
+ "image_gen": "<image_gen>",
184
+ "image_edit": "<image_edit>"
185
+ },
186
+ "generation": {
187
+ "max_new_tokens": 2048,
188
+ "temperature": 0.7,
189
+ "top_p": 0.9,
190
+ "do_sample": true
191
+ },
192
+ "image_generation": {
193
+ "default_height": 1024,
194
+ "default_width": 1024,
195
+ "num_inference_steps": 50,
196
+ "guidance_scale": 1.0,
197
+ "true_cfg_scale": 4.0
198
+ },
199
+ "system_prompt": "你是中国科学院磐石团队训练的 S1-Omni 统一架构多模态模型,具备多模态图像理解和生成能力。"
200
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.8,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.6"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
qwen3_config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "hidden_size": 5120,
8
+ "image_token_id": 151655,
9
+ "model_type": "qwen3_vl",
10
+ "pad_token_id": 151643,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 151643,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 151645,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 5120,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 25600,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "qwen3_vl_text",
24
+ "num_attention_heads": 64,
25
+ "num_hidden_layers": 64,
26
+ "num_key_value_heads": 8,
27
+ "pad_token_id": 151643,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_scaling": {
30
+ "mrope_interleaved": true,
31
+ "mrope_section": [
32
+ 24,
33
+ 20,
34
+ 20
35
+ ],
36
+ "rope_type": "default"
37
+ },
38
+ "rope_theta": 5000000,
39
+ "use_cache": false,
40
+ "vocab_size": 151936
41
+ },
42
+ "tie_word_embeddings": false,
43
+ "transformers_version": "4.57.6",
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 8,
48
+ 16,
49
+ 24
50
+ ],
51
+ "depth": 27,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1152,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4304,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 5120,
62
+ "pad_token_id": 151643,
63
+ "patch_size": 16,
64
+ "spatial_merge_size": 2,
65
+ "temporal_patch_size": 2
66
+ },
67
+ "vision_end_token_id": 151653,
68
+ "vision_start_token_id": 151652
69
+ }
scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlowMatchEulerDiscreteScheduler",
3
+ "_diffusers_version": "0.36.0.dev0",
4
+ "base_image_seq_len": 256,
5
+ "base_shift": 0.5,
6
+ "invert_sigmas": false,
7
+ "max_image_seq_len": 8192,
8
+ "max_shift": 0.9,
9
+ "num_train_timesteps": 1000,
10
+ "shift": 1.0,
11
+ "shift_terminal": 0.02,
12
+ "stochastic_sampling": false,
13
+ "time_shift_type": "exponential",
14
+ "use_beta_sigmas": false,
15
+ "use_dynamic_shifting": true,
16
+ "use_exponential_sigmas": false,
17
+ "use_karras_sigmas": false
18
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<image_gen>",
17
+ "<image_edit>"
18
+ ],
19
+ "eos_token": {
20
+ "content": "<|im_end|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": {
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deaafd7ac108862739c7cd0f24f8fe6ec6940cdd830a0b13e415631c07b91509
3
+ size 11423031
tokenizer_config.json ADDED
@@ -0,0 +1,258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<image_gen>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<image_edit>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>",
244
+ "<image_gen>",
245
+ "<image_edit>"
246
+ ],
247
+ "bos_token": null,
248
+ "clean_up_tokenization_spaces": false,
249
+ "eos_token": "<|im_end|>",
250
+ "errors": "replace",
251
+ "extra_special_tokens": {},
252
+ "model_max_length": 262144,
253
+ "pad_token": "<|endoftext|>",
254
+ "processor_class": "Qwen3VLProcessor",
255
+ "split_special_tokens": false,
256
+ "tokenizer_class": "Qwen2Tokenizer",
257
+ "unk_token": null
258
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff