lihongjie commited on
Commit
8728085
·
1 Parent(s): d24fafb

first commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ vocab.json filter=lfs diff=lfs merge=lfs -text
39
+ merges.txt filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set default_system_message = 'Represent the user\'s input.' -%}
2
+ {%- if tools %}
3
+ {{- '<|im_start|>system\n' }}
4
+ {%- if messages[0].role == 'system' %}
5
+ {%- if messages[0].content is string %}
6
+ {{- messages[0].content }}
7
+ {%- else %}
8
+ {%- for content in messages[0].content %}
9
+ {%- if 'text' in content %}
10
+ {{- content.text }}
11
+ {%- endif %}
12
+ {%- endfor %}
13
+ {%- endif %}
14
+ {{- '\n\n' }}
15
+ {%- else %}
16
+ {{- default_system_message + '\n\n' }}
17
+ {%- endif %}
18
+ {{- "# 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>" }}
19
+ {%- for tool in tools %}
20
+ {{- "\n" }}
21
+ {{- tool | tojson }}
22
+ {%- endfor %}
23
+ {{- "\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" }}
24
+ {%- else %}
25
+ {%- if messages[0].role == 'system' %}
26
+ {{- '<|im_start|>system\n' }}
27
+ {%- if messages[0].content is string %}
28
+ {{- messages[0].content }}
29
+ {%- else %}
30
+ {%- for content in messages[0].content %}
31
+ {%- if 'text' in content %}
32
+ {{- content.text }}
33
+ {%- endif %}
34
+ {%- endfor %}
35
+ {%- endif %}
36
+ {{- '<|im_end|>\n' }}
37
+ {%- else %}
38
+ {{- '<|im_start|>system\n' + default_system_message + '<|im_end|>\n' }}
39
+ {%- endif %}
40
+ {%- endif %}
41
+ {%- set image_count = namespace(value=0) %}
42
+ {%- set video_count = namespace(value=0) %}
43
+ {%- for message in messages %}
44
+ {%- if message.role == "user" %}
45
+ {{- '<|im_start|>' + message.role + '\n' }}
46
+ {%- if message.content is string %}
47
+ {{- message.content }}
48
+ {%- else %}
49
+ {%- for content in message.content %}
50
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
51
+ {%- set image_count.value = image_count.value + 1 %}
52
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
53
+ <|vision_start|><|image_pad|><|vision_end|>
54
+ {%- elif content.type == 'video' or 'video' in content %}
55
+ {%- set video_count.value = video_count.value + 1 %}
56
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
57
+ <|vision_start|><|video_pad|><|vision_end|>
58
+ {%- elif 'text' in content %}
59
+ {{- content.text }}
60
+ {%- endif %}
61
+ {%- endfor %}
62
+ {%- endif %}
63
+ {{- '<|im_end|>\n' }}
64
+ {%- elif message.role == "assistant" %}
65
+ {{- '<|im_start|>' + message.role + '\n' }}
66
+ {%- if message.content is string %}
67
+ {{- message.content }}
68
+ {%- else %}
69
+ {%- for content_item in message.content %}
70
+ {%- if 'text' in content_item %}
71
+ {{- content_item.text }}
72
+ {%- endif %}
73
+ {%- endfor %}
74
+ {%- endif %}
75
+ {%- if message.tool_calls %}
76
+ {%- for tool_call in message.tool_calls %}
77
+ {%- if (loop.first and message.content) or (not loop.first) %}
78
+ {{- '\n' }}
79
+ {%- endif %}
80
+ {%- if tool_call.function %}
81
+ {%- set tool_call = tool_call.function %}
82
+ {%- endif %}
83
+ {{- '<tool_call>\n{"name": "' }}
84
+ {{- tool_call.name }}
85
+ {{- '", "arguments": ' }}
86
+ {%- if tool_call.arguments is string %}
87
+ {{- tool_call.arguments }}
88
+ {%- else %}
89
+ {{- tool_call.arguments | tojson }}
90
+ {%- endif %}
91
+ {{- '}\n</tool_call>' }}
92
+ {%- endfor %}
93
+ {%- endif %}
94
+ {{- '<|im_end|>\n' }}
95
+ {%- elif message.role == "tool" %}
96
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
97
+ {{- '<|im_start|>user' }}
98
+ {%- endif %}
99
+ {{- '\n<tool_response>\n' }}
100
+ {%- if message.content is string %}
101
+ {{- message.content }}
102
+ {%- else %}
103
+ {%- for content in message.content %}
104
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
105
+ {%- set image_count.value = image_count.value + 1 %}
106
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
107
+ <|vision_start|><|image_pad|><|vision_end|>
108
+ {%- elif content.type == 'video' or 'video' in content %}
109
+ {%- set video_count.value = video_count.value + 1 %}
110
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
111
+ <|vision_start|><|video_pad|><|vision_end|>
112
+ {%- elif 'text' in content %}
113
+ {{- content.text }}
114
+ {%- endif %}
115
+ {%- endfor %}
116
+ {%- endif %}
117
+ {{- '\n</tool_response>' }}
118
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
119
+ {{- '<|im_end|>\n' }}
120
+ {%- endif %}
121
+ {%- endif %}
122
+ {%- endfor %}
123
+ {%- if add_generation_prompt %}
124
+ {{- '<|im_start|>assistant\n' }}
125
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen3_vl",
8
+ "quantization_config": {
9
+ "bits": 4,
10
+ "checkpoint_format": "gptq_v2",
11
+ "desc_act": false,
12
+ "format": "gptq_v2",
13
+ "group_size": 128,
14
+ "lm_head": false,
15
+ "meta": {
16
+ "act_group_aware": true,
17
+ "damp_auto_increment": 0.01,
18
+ "damp_percent": 0.05,
19
+ "gptaq": false,
20
+ "gptaq_alpha": 0.25,
21
+ "mse": 2.5,
22
+ "quantizer": [
23
+ "gptqmodel:5.6.12"
24
+ ],
25
+ "static_groups": true,
26
+ "true_sequential": true,
27
+ "uri": "https://github.com/modelcloud/gptqmodel"
28
+ },
29
+ "pack_dtype": "int32",
30
+ "pack_impl": "gpu",
31
+ "quant_method": "gptq",
32
+ "sym": true
33
+ },
34
+ "text_config": {
35
+ "attention_bias": false,
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "dtype": "bfloat16",
39
+ "eos_token_id": 151645,
40
+ "head_dim": 128,
41
+ "hidden_act": "silu",
42
+ "hidden_size": 2048,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 6144,
45
+ "max_position_embeddings": 262144,
46
+ "model_type": "qwen3_vl_text",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 8,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": {
52
+ "mrope_interleaved": true,
53
+ "mrope_section": [
54
+ 24,
55
+ 20,
56
+ 20
57
+ ],
58
+ "rope_type": "default"
59
+ },
60
+ "rope_theta": 5000000,
61
+ "tie_word_embeddings": true,
62
+ "use_cache": true,
63
+ "vocab_size": 151936
64
+ },
65
+ "tie_word_embeddings": true,
66
+ "transformers_version": "4.57.3",
67
+ "use_cache": false,
68
+ "video_token_id": 151656,
69
+ "vision_config": {
70
+ "deepstack_visual_indexes": [
71
+ 5,
72
+ 11,
73
+ 17
74
+ ],
75
+ "depth": 24,
76
+ "dtype": "bfloat16",
77
+ "hidden_act": "gelu_pytorch_tanh",
78
+ "hidden_size": 1024,
79
+ "in_channels": 3,
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 4096,
82
+ "model_type": "qwen3_vl",
83
+ "num_heads": 16,
84
+ "num_position_embeddings": 2304,
85
+ "out_hidden_size": 2048,
86
+ "patch_size": 16,
87
+ "spatial_merge_size": 2,
88
+ "temporal_patch_size": 2
89
+ },
90
+ "vision_end_token_id": 151653,
91
+ "vision_start_token_id": 151652
92
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": 151645,
6
+ "transformers_version": "4.57.3",
7
+ "use_cache": false
8
+ }
merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
3
+ size 1671853
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24692993925df638d499cb0865cb506cd9f2757f8f2a141c871f3170ef30a11e
3
+ size 2170874066
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 1310720,
26
+ "merge_size": 2,
27
+ "min_pixels": 4096,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 1310720,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
quantize_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "desc_act": false,
5
+ "sym": true,
6
+ "lm_head": false,
7
+ "quant_method": "gptq",
8
+ "checkpoint_format": "gptq_v2",
9
+ "pack_dtype": "int32",
10
+ "meta": {
11
+ "quantizer": [
12
+ "gptqmodel:5.6.12"
13
+ ],
14
+ "uri": "https://github.com/modelcloud/gptqmodel",
15
+ "damp_percent": 0.05,
16
+ "damp_auto_increment": 0.01,
17
+ "static_groups": true,
18
+ "true_sequential": true,
19
+ "mse": 2.5,
20
+ "gptaq": false,
21
+ "gptaq_alpha": 0.25,
22
+ "act_group_aware": true
23
+ },
24
+ "pack_impl": "gpu",
25
+ "format": "gptq_v2"
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|endoftext|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def76fb086971c7867b829c23a26261e38d9d74e02139253b38aeb9df8b4b50a
3
+ size 11423705
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2TokenizerFast",
238
+ "unk_token": null,
239
+ "_commit_hash": null
240
+ }
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
3
+ size 2776833