Yang-Zhou commited on
Commit
a6dec3d
·
verified ·
1 Parent(s): 355568f

Add files using upload-large-folder tool

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
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 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
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": 4096,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 12288,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "qwen3_vl_text",
24
+ "num_attention_heads": 32,
25
+ "num_hidden_layers": 36,
26
+ "num_key_value_heads": 8,
27
+ "pad_token_id": null,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_parameters": {
30
+ "mrope_interleaved": true,
31
+ "mrope_section": [
32
+ 24,
33
+ 20,
34
+ 20
35
+ ],
36
+ "rope_theta": 5000000,
37
+ "rope_type": "default"
38
+ },
39
+ "use_cache": true,
40
+ "vocab_size": 151936
41
+ },
42
+ "tie_word_embeddings": false,
43
+ "transformers_version": "5.5.4",
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": 4096,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "repetition_penalty": 1.0,
10
+ "temperature": 1.0,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.5.4"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12ca8db3dc2f519878ef756d781c4e5aea635bc564d9171181e0ca6f7cc86ff
3
+ size 17534340584
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "model_max_length": 262144,
25
+ "pad_token": "<|endoftext|>",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }