VoyagerXHF commited on
Commit
72a217a
·
verified ·
1 Parent(s): 69b8fb7

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
chat_template.jinja ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 'audio' in item or item.type == 'audio' %}
31
+ {%- if is_system_content %}
32
+ {{- raise_exception('System message cannot contain audio.') }}
33
+ {%- endif %}
34
+ {{- '<|audio_start|><|audio_pad|><|audio_end|>' }}
35
+ {%- elif 'text' in item %}
36
+ {{- item.text }}
37
+ {%- else %}
38
+ {{- raise_exception('Unexpected item type in content.') }}
39
+ {%- endif %}
40
+ {%- endfor %}
41
+ {%- elif content is none or content is undefined %}
42
+ {{- '' }}
43
+ {%- else %}
44
+ {{- raise_exception('Unexpected content type.') }}
45
+ {%- endif %}
46
+ {%- endmacro %}
47
+ {#- Dynamic reasoning_effort (low/high/xhigh): low & xhigh inject a system directive line; high or unset = no injection (== high). #}
48
+ {%- if reasoning_effort is defined and reasoning_effort is not none %}
49
+ {%- if reasoning_effort not in ['low', 'high', 'xhigh'] %}
50
+ {{- raise_exception('Unknown reasoning_effort: ' + reasoning_effort|string + '. Expected one of: low, high, xhigh.') }}
51
+ {%- endif %}
52
+ {%- endif %}
53
+ {%- set add_reasoning = reasoning_effort is defined and reasoning_effort is not none and reasoning_effort in ['low', 'xhigh'] %}
54
+ {%- if add_reasoning %}
55
+ {%- if reasoning_effort == 'low' %}
56
+ {%- set reasoning_line = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
57
+ {%- elif reasoning_effort == 'xhigh' %}
58
+ {%- set reasoning_line = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
59
+ {%- endif %}
60
+ {%- set reasoning_prefix = reasoning_line + '\n\n' %}
61
+ {%- else %}
62
+ {%- set reasoning_prefix = '' %}
63
+ {%- endif %}
64
+ {%- if not messages %}
65
+ {{- raise_exception('No messages provided.') }}
66
+ {%- endif %}
67
+ {%- if tools and tools is iterable and tools is not mapping %}
68
+ {{- '<|im_start|>system\n' }}
69
+ {{- reasoning_prefix }}
70
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
71
+ {%- for tool in tools %}
72
+ {{- "\n" }}
73
+ {{- tool | tojson }}
74
+ {%- endfor %}
75
+ {{- "\n</tools>" }}
76
+ {{- '\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>' }}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '\n\n' + content }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {{- '<|im_end|>\n' }}
84
+ {%- else %}
85
+ {%- if messages[0].role == 'system' %}
86
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
87
+ {{- '<|im_start|>system\n' + reasoning_prefix + content + '<|im_end|>\n' }}
88
+ {%- elif add_reasoning %}
89
+ {{- '<|im_start|>system\n' + reasoning_line + '<|im_end|>\n' }}
90
+ {%- endif %}
91
+ {%- endif %}
92
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
93
+ {%- for message in messages[::-1] %}
94
+ {%- set index = (messages|length - 1) - loop.index0 %}
95
+ {%- if ns.multi_step_tool and message.role == "user" %}
96
+ {%- set content = render_content(message.content, false)|trim %}
97
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
98
+ {%- set ns.multi_step_tool = false %}
99
+ {%- set ns.last_query_index = index %}
100
+ {%- endif %}
101
+ {%- endif %}
102
+ {%- endfor %}
103
+ {%- if ns.multi_step_tool %}
104
+ {{- raise_exception('No user query found in messages.') }}
105
+ {%- endif %}
106
+ {%- for message in messages %}
107
+ {%- set content = render_content(message.content, true)|trim %}
108
+ {%- if message.role == "system" %}
109
+ {%- if not loop.first %}
110
+ {{- raise_exception('System message must be at the beginning.') }}
111
+ {%- endif %}
112
+ {%- elif message.role == "user" %}
113
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
114
+ {%- elif message.role == "assistant" %}
115
+ {%- set reasoning_content = '' %}
116
+ {%- if message.reasoning_content is string %}
117
+ {%- set reasoning_content = message.reasoning_content %}
118
+ {%- else %}
119
+ {%- if '</think>' in content %}
120
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
121
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
122
+ {%- endif %}
123
+ {%- endif %}
124
+ {%- set reasoning_content = reasoning_content|trim %}
125
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
126
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
127
+ {%- else %}
128
+ {{- '<|im_start|>' + message.role + '\n' + content }}
129
+ {%- endif %}
130
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
131
+ {%- for tool_call in message.tool_calls %}
132
+ {%- if tool_call.function is defined %}
133
+ {%- set tool_call = tool_call.function %}
134
+ {%- endif %}
135
+ {%- if loop.first %}
136
+ {%- if content|trim %}
137
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
138
+ {%- else %}
139
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
140
+ {%- endif %}
141
+ {%- else %}
142
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
143
+ {%- endif %}
144
+ {%- if tool_call.arguments is defined %}
145
+ {%- for args_name, args_value in tool_call.arguments|items %}
146
+ {{- '<parameter=' + args_name + '>\n' }}
147
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
148
+ {{- args_value }}
149
+ {{- '\n</parameter>\n' }}
150
+ {%- endfor %}
151
+ {%- endif %}
152
+ {{- '</function>\n</tool_call>' }}
153
+ {%- endfor %}
154
+ {%- endif %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif message.role == "tool" %}
157
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
158
+ {{- '<|im_start|>user' }}
159
+ {%- endif %}
160
+ {{- '\n<tool_response>\n' }}
161
+ {{- content }}
162
+ {{- '\n</tool_response>' }}
163
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
164
+ {{- '<|im_end|>\n' }}
165
+ {%- elif loop.last %}
166
+ {{- '<|im_end|>\n' }}
167
+ {%- endif %}
168
+ {%- else %}
169
+ {{- raise_exception('Unexpected message role.') }}
170
+ {%- endif %}
171
+ {%- endfor %}
172
+ {%- if add_generation_prompt %}
173
+ {{- '<|im_start|>assistant\n' }}
174
+ {%- if enable_thinking is defined and enable_thinking is false %}
175
+ {{- '<think>\n\n</think>\n\n' }}
176
+ {%- else %}
177
+ {{- '<think>\n' }}
178
+ {%- endif %}
179
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "language_model_only": false,
7
+ "model_type": "qwen3_5",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "attn_output_gate": true,
12
+ "bos_token_id": 248044,
13
+ "dtype": "bfloat16",
14
+ "eos_token_id": 248044,
15
+ "full_attention_interval": 4,
16
+ "head_dim": 256,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 5120,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 17408,
21
+ "layer_types": [
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "full_attention"
86
+ ],
87
+ "linear_conv_kernel_dim": 4,
88
+ "linear_key_head_dim": 128,
89
+ "linear_num_key_heads": 16,
90
+ "linear_num_value_heads": 48,
91
+ "linear_value_head_dim": 128,
92
+ "mamba_ssm_dtype": "float32",
93
+ "max_position_embeddings": 262144,
94
+ "model_type": "qwen3_5_text",
95
+ "mtp_num_hidden_layers": 1,
96
+ "mtp_use_dedicated_embeddings": false,
97
+ "num_attention_heads": 24,
98
+ "num_hidden_layers": 64,
99
+ "num_key_value_heads": 4,
100
+ "output_gate_type": "swish",
101
+ "pad_token_id": null,
102
+ "partial_rotary_factor": 0.25,
103
+ "rms_norm_eps": 1e-06,
104
+ "rope_parameters": {
105
+ "mrope_interleaved": true,
106
+ "mrope_section": [
107
+ 11,
108
+ 11,
109
+ 10
110
+ ],
111
+ "partial_rotary_factor": 0.25,
112
+ "rope_theta": 10000000,
113
+ "rope_type": "default"
114
+ },
115
+ "tie_word_embeddings": false,
116
+ "use_cache": true,
117
+ "vocab_size": 248320
118
+ },
119
+ "tie_word_embeddings": false,
120
+ "transformers_version": "5.8.0.dev0",
121
+ "video_token_id": 248057,
122
+ "vision_config": {
123
+ "deepstack_visual_indexes": [],
124
+ "depth": 27,
125
+ "hidden_act": "gelu_pytorch_tanh",
126
+ "hidden_size": 1152,
127
+ "in_channels": 3,
128
+ "initializer_range": 0.02,
129
+ "intermediate_size": 4304,
130
+ "model_type": "qwen3_5",
131
+ "num_heads": 16,
132
+ "num_position_embeddings": 2304,
133
+ "out_hidden_size": 5120,
134
+ "patch_size": 16,
135
+ "spatial_merge_size": 2,
136
+ "temporal_patch_size": 2
137
+ },
138
+ "vision_end_token_id": 248054,
139
+ "vision_start_token_id": 248053
140
+ }
crc32.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ cf59f3ab chat_template.jinja
2
+ ac8d98f1 generation_config.json
3
+ 1824fcb5 merges.txt
4
+ 030e383a preprocessor_config.json
5
+ 6b61f895 tokenizer.json
6
+ 7adf2118 tokenizer_config.json
7
+ 44c041dc video_preprocessor_config.json
8
+ da8db314 vocab.json
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0ce20aae489ad196733da5064bcdf159a1fe84f53336648196e1ebb7751b1c
3
+ size 3966730552
model-00002-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a148c01bfbe3faa14a5f184a7ff29a706f7ae1c8b2705d2058e26d17a001fb
3
+ size 3043080328
model-00003-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1bf62cbcd406eaa64b60d10353e1f0ef4039d0976e56f05cabe953454f9968
3
+ size 2542796952
model-00004-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511e34063187882659753c4d93f3859f93c019fd438d8813071921c81d9a3f1a
3
+ size 3988973152
model-00005-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635cb53446dc74f219740fc59e18b774f877b803b9722e289ca62575a6efa701
3
+ size 2099339864
model-00006-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc5214fac607f0e6cc92eec3789d4b8559410ef9fce66621ba8158e8410dae0
3
+ size 3979553696
model-00007-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b0c49033e9a0d5762562aa12f4acdb7f54da586f3d0110f28c48d91cf07892
3
+ size 2108759344
model-00008-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7192c5b66185d3592927daabee1cc19e6f6e0ce75988ee20e824b624765fda79
3
+ size 3979553696
model-00009-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3c48cc37af44f3db6ae0579baf019180d48d9c527caa0a1f03ff85813a56d8
3
+ size 2108759344
model-00010-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163490a76f3bea3a40855b7efc04ce6d27afaf1a34f0bbde495b9491f76457c9
3
+ size 3979553696
model-00011-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3ae1b948aeee39da77aec558e8236cd65fe4d7cb7686a76bb007acc563c6d8
3
+ size 2108759344
model-00012-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3de1c7114677a8f5ac5c4892c90e8238ea5c1e2038c80e757dfc87c3902ca55
3
+ size 3979553696
model-00013-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ab79a41f74c9c5cb734816feb0c7fc364104b227165ee7391231e1155aa02a
3
+ size 2108759344
model-00014-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4138ed94603065ba884bbcadedb04d7718bb40117e85e6f5c6fc5b9c05b7a85b
3
+ size 3979553696
model-00015-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69224e27b9de4e7dbf6fc936c6eaae08447bda3b80a6c31a871ab451173afd22
3
+ size 2108759344
model-00016-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73cb9a1089fb6155cb648609478d6633be8a5c7d9ca5a05bc8925ce8a553cefe
3
+ size 3979564040
model-00017-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb51f01056142ac4984bd800507b0dd0fd18de57f8e9ef6ea41d1a3598983a8
3
+ size 2108759344
model-00018-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3479509e21494658f9b64d317f5ea8e55c4025d28c702d6c4d0b356ce8ea06
3
+ size 3392197344
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
3
+ size 12809320
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'audio' in item or item.type == 'audio' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain audio.') }}\n {%- endif %}\n {{- '<|audio_start|><|audio_pad|><|audio_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{#- Dynamic reasoning_effort (low/high/xhigh): low & xhigh inject a system directive line; high or unset = no injection (== high). #}\n{%- if reasoning_effort is defined and reasoning_effort is not none %}\n {%- if reasoning_effort not in ['low', 'high', 'xhigh'] %}\n {{- raise_exception('Unknown reasoning_effort: ' + reasoning_effort|string + '. Expected one of: low, high, xhigh.') }}\n {%- endif %}\n{%- endif %}\n{%- set add_reasoning = reasoning_effort is defined and reasoning_effort is not none and reasoning_effort in ['low', 'xhigh'] %}\n{%- if add_reasoning %}\n {%- if reasoning_effort == 'low' %}\n {%- set reasoning_line = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n {%- elif reasoning_effort == 'xhigh' %}\n {%- set reasoning_line = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n {%- endif %}\n {%- set reasoning_prefix = reasoning_line + '\\n\\n' %}\n{%- else %}\n {%- set reasoning_prefix = '' %}\n{%- endif %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- reasoning_prefix }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\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>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {{- '<|im_start|>system\\n' + reasoning_prefix + content + '<|im_end|>\\n' }}\n {%- elif add_reasoning %}\n {{- '<|im_start|>system\\n' + reasoning_line + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 131072,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "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+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
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
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff