Hugging Face's logo

br1-pist
/
Qwen3.5-4B-AgentCoder

Image-Text-to-Text
Safetensors
English
qwen3_5
agent
code
conversational
Model card Files
xet
 Community
br1-pist commited on
Commit
9b24be8
·
verified ·
1 Parent(s): e5eb7f5

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +105 -100
  2. generation_config.json +6 -0
  3. model-00001-of-00005.safetensors +3 -0
  4. model-00002-of-00005.safetensors +3 -0
  5. model-00003-of-00005.safetensors +3 -0
  6. model-00004-of-00005.safetensors +3 -0
  7. model-00005-of-00005.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. preprocessor_config.json +26 -20
  10. processor_config.json +63 -0
  11. tokenizer.json +2 -2
  12. tokenizer_config.json +31 -304
  13. video_preprocessor_config.json +32 -20
config.json CHANGED
@@ -1,104 +1,109 @@
1
  {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
- "image_token_id": 248056,
6
- "model_type": "qwen3_5",
7
- "text_config": {
8
- "attention_bias": false,
9
- "attention_dropout": 0.0,
10
- "attn_output_gate": true,
11
- "dtype": "bfloat16",
12
- "eos_token_id": 248044,
13
- "full_attention_interval": 4,
14
- "head_dim": 256,
15
- "hidden_act": "silu",
16
- "hidden_size": 2560,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 9216,
19
- "layer_types": [
20
- "linear_attention",
21
- "linear_attention",
22
- "linear_attention",
23
- "full_attention",
24
- "linear_attention",
25
- "linear_attention",
26
- "linear_attention",
27
- "full_attention",
28
- "linear_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "full_attention",
32
- "linear_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "full_attention",
36
- "linear_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "full_attention",
40
- "linear_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "full_attention",
44
- "linear_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "full_attention",
48
- "linear_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "full_attention"
52
- ],
53
- "linear_conv_kernel_dim": 4,
54
- "linear_key_head_dim": 128,
55
- "linear_num_key_heads": 16,
56
- "linear_num_value_heads": 32,
57
- "linear_value_head_dim": 128,
58
- "max_position_embeddings": 262144,
59
- "mlp_only_layers": [],
60
- "model_type": "qwen3_5_text",
61
- "mtp_num_hidden_layers": 1,
62
- "mtp_use_dedicated_embeddings": false,
63
- "num_attention_heads": 16,
64
- "num_hidden_layers": 32,
65
- "num_key_value_heads": 4,
66
- "rms_norm_eps": 1e-06,
67
- "tie_word_embeddings": true,
68
- "use_cache": true,
69
- "vocab_size": 248320,
70
- "mamba_ssm_dtype": "float32",
71
- "rope_parameters": {
72
- "mrope_interleaved": true,
73
- "mrope_section": [
74
- 11,
75
- 11,
76
- 10
77
- ],
78
- "rope_type": "default",
79
- "rope_theta": 10000000,
80
- "partial_rotary_factor": 0.25
81
- }
82
  },
83
  "tie_word_embeddings": true,
84
- "transformers_version": "4.57.0.dev0",
85
- "video_token_id": 248057,
86
- "vision_config": {
87
- "deepstack_visual_indexes": [],
88
- "depth": 24,
89
- "hidden_act": "gelu_pytorch_tanh",
90
- "hidden_size": 1024,
91
- "in_channels": 3,
92
- "initializer_range": 0.02,
93
- "intermediate_size": 4096,
94
- "model_type": "qwen3_5",
95
- "num_heads": 16,
96
- "num_position_embeddings": 2304,
97
- "out_hidden_size": 2560,
98
- "patch_size": 16,
99
- "spatial_merge_size": 2,
100
- "temporal_patch_size": 2
101
- },
102
- "vision_end_token_id": 248054,
103
- "vision_start_token_id": 248053
104
- }
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
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": null,
13
+ "dtype": "bfloat16",
14
+ "eos_token_id": 248044,
15
+ "full_attention_interval": 4,
16
+ "head_dim": 256,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2560,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 9216,
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
  ],
55
+ "linear_conv_kernel_dim": 4,
56
+ "linear_key_head_dim": 128,
57
+ "linear_num_key_heads": 16,
58
+ "linear_num_value_heads": 32,
59
+ "linear_value_head_dim": 128,
60
+ "mamba_ssm_dtype": "float32",
61
+ "max_position_embeddings": 262144,
62
+ "mlp_only_layers": [],
63
+ "model_type": "qwen3_5_text",
64
+ "mtp_num_hidden_layers": 1,
65
+ "mtp_use_dedicated_embeddings": false,
66
+ "num_attention_heads": 16,
67
+ "num_hidden_layers": 32,
68
+ "num_key_value_heads": 4,
69
+ "pad_token_id": null,
70
+ "partial_rotary_factor": 0.25,
71
+ "rms_norm_eps": 1e-06,
72
+ "rope_parameters": {
73
+ "mrope_interleaved": true,
74
+ "mrope_section": [
75
+ 11,
76
+ 11,
77
+ 10
78
+ ],
79
+ "partial_rotary_factor": 0.25,
80
+ "rope_theta": 10000000,
81
+ "rope_type": "default"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
  },
83
  "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "vocab_size": 248320
86
+ },
87
+ "tie_word_embeddings": true,
88
+ "transformers_version": "5.3.0",
89
+ "video_token_id": 248057,
90
+ "vision_config": {
91
+ "deepstack_visual_indexes": [],
92
+ "depth": 24,
93
+ "dtype": "bfloat16",
94
+ "hidden_act": "gelu_pytorch_tanh",
95
+ "hidden_size": 1024,
96
+ "in_channels": 3,
97
+ "initializer_range": 0.02,
98
+ "intermediate_size": 4096,
99
+ "model_type": "qwen3_5",
100
+ "num_heads": 16,
101
+ "num_position_embeddings": 2304,
102
+ "out_hidden_size": 2560,
103
+ "patch_size": 16,
104
+ "spatial_merge_size": 2,
105
+ "temporal_patch_size": 2
106
+ },
107
+ "vision_end_token_id": 248054,
108
+ "vision_start_token_id": 248053
109
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 248044,
4
+ "transformers_version": "5.3.0",
5
+ "use_cache": true
6
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d74aba621b2807aa1a713d8d43ff6355fa69ace74488f20bf959c727058443ae
3
+ size 1996138368
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ec9dcf87eaf8bfc80502f0c7fd7b2c4154f3fd7c96ae75400d020f5b76a54f
3
+ size 1995160352
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da494ee2404ab9c3a8be1815413dd61211eb079960bd3c17b50cce46265e6b8a
3
+ size 1968944944
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2db57faa12c5750ea8fd55ce1fd78d70497665db8977bf940133badcc654ec5
3
+ size 1963297576
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84dd2b770e12a869a6c028cbbceadf23b1f53751222a09800c51e5b3b272ef64
3
+ size 1155078448
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json CHANGED
@@ -1,21 +1,27 @@
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
- }
 
 
 
 
 
 
 
1
  {
2
+ "data_format": "channels_first",
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": "Qwen2VLImageProcessorFast",
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
+ }
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
- size 12807982
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json CHANGED
@@ -1,305 +1,32 @@
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 '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{%- 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 {{- \"# 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' + content + '<|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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\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": 262144,
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
- }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "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+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
video_preprocessor_config.json CHANGED
@@ -1,21 +1,33 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "data_format": "channels_first",
3
+ "default_to_square": true,
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "do_sample_frames": true,
9
+ "fps": 2,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "max_frames": 768,
21
+ "merge_size": 2,
22
+ "min_frames": 4,
23
+ "patch_size": 16,
24
+ "resample": 3,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "return_metadata": false,
27
+ "size": {
28
+ "longest_edge": 25165824,
29
+ "shortest_edge": 4096
30
+ },
31
+ "temporal_patch_size": 2,
32
+ "video_processor_type": "Qwen3VLVideoProcessor"
33
+ }