Hugging Face's logo

inclusionAI
/
ZwZ-2B

Image-Text-to-Text
Transformers
Safetensors
English
qwen3_vl
conversational
Model card Files
xet
 Community
langdaohlb commited on
Commit
e6ade8d
·
verified ·
1 Parent(s): 0547e88

delete wrong files

Browse files
Files changed (12) hide show
  1. ZwZ-2B/added_tokens.json +0 -28
  2. ZwZ-2B/chat_template.jinja +0 -120
  3. ZwZ-2B/config.json +0 -67
  4. ZwZ-2B/generation_config.json +0 -7
  5. ZwZ-2B/merges.txt +0 -0
  6. ZwZ-2B/model.safetensors +0 -3
  7. ZwZ-2B/preprocessor_config.json +0 -39
  8. ZwZ-2B/special_tokens_map.json +0 -31
  9. ZwZ-2B/tokenizer.json +0 -3
  10. ZwZ-2B/tokenizer_config.json +0 -241
  11. ZwZ-2B/video_preprocessor_config.json +0 -41
  12. ZwZ-2B/vocab.json +0 -0
ZwZ-2B/added_tokens.json DELETED
@@ -1,28 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/chat_template.jinja DELETED
@@ -1,120 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {%- if messages[0].content is string %}
5
- {{- messages[0].content }}
6
- {%- else %}
7
- {%- for content in messages[0].content %}
8
- {%- if 'text' in content %}
9
- {{- content.text }}
10
- {%- endif %}
11
- {%- endfor %}
12
- {%- endif %}
13
- {{- '\n\n' }}
14
- {%- endif %}
15
- {{- "# 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>" }}
16
- {%- for tool in tools %}
17
- {{- "\n" }}
18
- {{- tool | tojson }}
19
- {%- endfor %}
20
- {{- "\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" }}
21
- {%- else %}
22
- {%- if messages[0].role == 'system' %}
23
- {{- '<|im_start|>system\n' }}
24
- {%- if messages[0].content is string %}
25
- {{- messages[0].content }}
26
- {%- else %}
27
- {%- for content in messages[0].content %}
28
- {%- if 'text' in content %}
29
- {{- content.text }}
30
- {%- endif %}
31
- {%- endfor %}
32
- {%- endif %}
33
- {{- '<|im_end|>\n' }}
34
- {%- endif %}
35
- {%- endif %}
36
- {%- set image_count = namespace(value=0) %}
37
- {%- set video_count = namespace(value=0) %}
38
- {%- for message in messages %}
39
- {%- if message.role == "user" %}
40
- {{- '<|im_start|>' + message.role + '\n' }}
41
- {%- if message.content is string %}
42
- {{- message.content }}
43
- {%- else %}
44
- {%- for content in message.content %}
45
- {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
- {%- set image_count.value = image_count.value + 1 %}
47
- {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
- <|vision_start|><|image_pad|><|vision_end|>
49
- {%- elif content.type == 'video' or 'video' in content %}
50
- {%- set video_count.value = video_count.value + 1 %}
51
- {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
- <|vision_start|><|video_pad|><|vision_end|>
53
- {%- elif 'text' in content %}
54
- {{- content.text }}
55
- {%- endif %}
56
- {%- endfor %}
57
- {%- endif %}
58
- {{- '<|im_end|>\n' }}
59
- {%- elif message.role == "assistant" %}
60
- {{- '<|im_start|>' + message.role + '\n' }}
61
- {%- if message.content is string %}
62
- {{- message.content }}
63
- {%- else %}
64
- {%- for content_item in message.content %}
65
- {%- if 'text' in content_item %}
66
- {{- content_item.text }}
67
- {%- endif %}
68
- {%- endfor %}
69
- {%- endif %}
70
- {%- if message.tool_calls %}
71
- {%- for tool_call in message.tool_calls %}
72
- {%- if (loop.first and message.content) or (not loop.first) %}
73
- {{- '\n' }}
74
- {%- endif %}
75
- {%- if tool_call.function %}
76
- {%- set tool_call = tool_call.function %}
77
- {%- endif %}
78
- {{- '<tool_call>\n{"name": "' }}
79
- {{- tool_call.name }}
80
- {{- '", "arguments": ' }}
81
- {%- if tool_call.arguments is string %}
82
- {{- tool_call.arguments }}
83
- {%- else %}
84
- {{- tool_call.arguments | tojson }}
85
- {%- endif %}
86
- {{- '}\n</tool_call>' }}
87
- {%- endfor %}
88
- {%- endif %}
89
- {{- '<|im_end|>\n' }}
90
- {%- elif message.role == "tool" %}
91
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
- {{- '<|im_start|>user' }}
93
- {%- endif %}
94
- {{- '\n<tool_response>\n' }}
95
- {%- if message.content is string %}
96
- {{- message.content }}
97
- {%- else %}
98
- {%- for content in message.content %}
99
- {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
- {%- set image_count.value = image_count.value + 1 %}
101
- {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
- <|vision_start|><|image_pad|><|vision_end|>
103
- {%- elif content.type == 'video' or 'video' in content %}
104
- {%- set video_count.value = video_count.value + 1 %}
105
- {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
- <|vision_start|><|video_pad|><|vision_end|>
107
- {%- elif 'text' in content %}
108
- {{- content.text }}
109
- {%- endif %}
110
- {%- endfor %}
111
- {%- endif %}
112
- {{- '\n</tool_response>' }}
113
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
- {{- '<|im_end|>\n' }}
115
- {%- endif %}
116
- {%- endif %}
117
- {%- endfor %}
118
- {%- if add_generation_prompt %}
119
- {{- '<|im_start|>assistant\n' }}
120
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/config.json DELETED
@@ -1,67 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3VLForConditionalGeneration"
4
- ],
5
- "dtype": "float32",
6
- "eos_token_id": 151645,
7
- "image_token_id": 151655,
8
- "model_type": "qwen3_vl",
9
- "pad_token_id": 151643,
10
- "text_config": {
11
- "attention_bias": false,
12
- "attention_dropout": 0.0,
13
- "bos_token_id": 151643,
14
- "dtype": "float32",
15
- "eos_token_id": 151645,
16
- "head_dim": 128,
17
- "hidden_act": "silu",
18
- "hidden_size": 2048,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 6144,
21
- "max_position_embeddings": 262144,
22
- "model_type": "qwen3_vl_text",
23
- "num_attention_heads": 16,
24
- "num_hidden_layers": 28,
25
- "num_key_value_heads": 8,
26
- "rms_norm_eps": 1e-06,
27
- "rope_scaling": {
28
- "mrope_interleaved": true,
29
- "mrope_section": [
30
- 24,
31
- 20,
32
- 20
33
- ],
34
- "rope_type": "default"
35
- },
36
- "rope_theta": 5000000,
37
- "tie_word_embeddings": true,
38
- "use_cache": true,
39
- "vocab_size": 151936
40
- },
41
- "tie_word_embeddings": true,
42
- "transformers_version": "4.57.1",
43
- "video_token_id": 151656,
44
- "vision_config": {
45
- "deepstack_visual_indexes": [
46
- 5,
47
- 11,
48
- 17
49
- ],
50
- "depth": 24,
51
- "dtype": "float32",
52
- "hidden_act": "gelu_pytorch_tanh",
53
- "hidden_size": 1024,
54
- "in_channels": 3,
55
- "initializer_range": 0.02,
56
- "intermediate_size": 4096,
57
- "model_type": "qwen3_vl",
58
- "num_heads": 16,
59
- "num_position_embeddings": 2304,
60
- "out_hidden_size": 2048,
61
- "patch_size": 16,
62
- "spatial_merge_size": 2,
63
- "temporal_patch_size": 2
64
- },
65
- "vision_end_token_id": 151653,
66
- "vision_start_token_id": 151652
67
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 151643,
4
- "eos_token_id": 151645,
5
- "pad_token_id": 151643,
6
- "transformers_version": "4.57.1"
7
- }
 
 
 
 
 
 
 
 
ZwZ-2B/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
ZwZ-2B/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a968d09de68912789050b3c7c847a28bbab31678b278db49e7fc1582fb81b8
3
- size 4877470336
 
 
 
 
ZwZ-2B/preprocessor_config.json DELETED
@@ -1,39 +0,0 @@
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": null,
26
- "merge_size": 2,
27
- "min_pixels": null,
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": 16777216,
36
- "shortest_edge": 65536
37
- },
38
- "temporal_patch_size": 2
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
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": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
ZwZ-2B/tokenizer_config.json DELETED
@@ -1,241 +0,0 @@
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
- "processor_class": "Qwen3VLProcessor",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null,
240
- "use_fast": true
241
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/video_preprocessor_config.json DELETED
@@ -1,41 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ZwZ-2B/vocab.json DELETED
The diff for this file is too large to render. See raw diff