Hugging Face's logo

Qwen
/
Qwen3-Omni-30B-A3B-Captioner

Any-to-Any
Transformers
Safetensors
English
qwen3_omni_moe
text-to-audio
multimodal
Model card Files
xet
Community
4
littlebird13 commited on
Commit
e8d13a3
·
verified ·
1 Parent(s): 417b6f7

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. chat_template.json +1 -0
  2. config.json +297 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. model-00001-of-00016.safetensors +3 -0
  6. model-00002-of-00016.safetensors +3 -0
  7. model-00003-of-00016.safetensors +3 -0
  8. model-00004-of-00016.safetensors +3 -0
  9. model-00005-of-00016.safetensors +3 -0
  10. model-00006-of-00016.safetensors +3 -0
  11. model-00007-of-00016.safetensors +3 -0
  12. model-00008-of-00016.safetensors +3 -0
  13. model-00009-of-00016.safetensors +3 -0
  14. model-00010-of-00016.safetensors +3 -0
  15. model-00011-of-00016.safetensors +3 -0
  16. model-00012-of-00016.safetensors +3 -0
  17. model-00013-of-00016.safetensors +3 -0
  18. model-00014-of-00016.safetensors +3 -0
  19. model-00015-of-00016.safetensors +3 -0
  20. model-00016-of-00016.safetensors +3 -0
  21. model.safetensors.index.json +0 -0
  22. preprocessor_config.json +30 -0
  23. tokenizer_config.json +316 -0
  24. vocab.json +0 -0
chat_template.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}{{- messages[0].content + '\\n\\n' }}{%- endif %}\n {{- \"# 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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {{- '<|im_start|>system\\n' +\"<|vision_start|><|image_pad|><|vision_end|>\"+ '<|im_end|>\\n' }}\n {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}\n {{- '<|im_start|>system\\n' +\"<|audio_start|><|audio_pad|><|audio_end|>\"+ '<|im_end|>\\n' }}\n {%- elif content.type == 'video' or 'video' in content %}\n {{- '<|im_start|>system\\n' +\"<|vision_start|><|video_pad|><|vision_end|>\"+ '<|im_end|>\\n' }}\n {%- elif content.type == 'text' %}\n {{- '<|im_start|>system\\n' +content.text+ '<|im_end|>\\n' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\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\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = namespace(text=\"\") %}\n {%- for mcontent in message.content %}\n {%- if mcontent.type == 'image' or 'image' in mcontent or 'image_url' in mcontent %}\n {%- set content.text = content.text~\"<|vision_start|><|image_pad|><|vision_end|>\" %}\n {%- elif mcontent.type == 'audio' or 'audio' in mcontent or 'audio_url' in mcontent %}\n {%- set content.text = content.text~\"<|audio_start|><|audio_pad|><|audio_end|>\" %}\n {%- elif mcontent.type == 'video' or 'video' in mcontent %}\n {%- set content.text = content.text~\"<|vision_start|><|video_pad|><|vision_end|>\" %}\n {%- elif mcontent.type == 'text' %}\n {%- set content.text = content.text~mcontent.text %}\n {%- endif %}\n {%- endfor %}\n {%- set content = content.text %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\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 {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip(\"\\n\") + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}{{- '\\n' }}{%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}{{- '<|im_start|>user' }}{%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}{{- '<|im_end|>\\n' }}{%- endif %}\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 %}{{- '<think>\\n\\n</think>\\n\\n' }}{%- endif %}\n{%- endif %}\n"}
config.json ADDED
@@ -0,0 +1,297 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3OmniMoeForConditionalGeneration"
4
+ ],
5
+ "assistant_token_id": 77091,
6
+ "dtype": "bfloat16",
7
+ "enable_audio_output": false,
8
+ "im_end_token_id": 151645,
9
+ "im_start_token_id": 151644,
10
+ "model_type": "qwen3_omni_moe",
11
+ "system_token_id": 8948,
12
+ "thinker_config": {
13
+ "audio_config": {
14
+ "_name_or_path": "",
15
+ "activation_dropout": 0,
16
+ "activation_function": "gelu",
17
+ "add_cross_attention": false,
18
+ "architectures": null,
19
+ "attention_dropout": 0,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": null,
23
+ "chunk_size_feed_forward": 0,
24
+ "conv_chunksize": 500,
25
+ "cross_attention_hidden_size": null,
26
+ "d_model": 1280,
27
+ "decoder_start_token_id": null,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "downsample_hidden_size":480,
31
+ "dropout": 0,
32
+ "dtype": null,
33
+ "early_stopping": false,
34
+ "encoder_attention_heads": 20,
35
+ "encoder_ffn_dim": 5120,
36
+ "encoder_layers": 32,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": null,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1"
46
+ },
47
+ "initializer_range": 0.02,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_source_positions": 1500,
57
+ "min_length": 0,
58
+ "model_type": "qwen3_omni_moe_audio_encoder",
59
+ "n_window": 50,
60
+ "n_window_infer": 800,
61
+ "no_repeat_ngram_size": 0,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_hidden_layers": 32,
65
+ "num_mel_bins": 128,
66
+ "num_return_sequences": 1,
67
+ "output_attentions": false,
68
+ "output_dim": 2048,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": null,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "remove_invalid_values": false,
76
+ "repetition_penalty": 1.0,
77
+ "return_dict": true,
78
+ "return_dict_in_generate": false,
79
+ "scale_embedding": false,
80
+ "sep_token_id": null,
81
+ "suppress_tokens": null,
82
+ "task_specific_params": null,
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torchscript": false,
91
+ "typical_p": 1.0,
92
+ "use_bfloat16": false
93
+ },
94
+ "audio_end_token_id": 151670,
95
+ "audio_start_token_id": 151669,
96
+ "audio_token_id": 151675,
97
+ "dtype": "bfloat16",
98
+ "image_token_id": 151655,
99
+ "initializer_range": 0.02,
100
+ "model_type": "qwen3_omni_moe_thinker",
101
+ "position_id_per_seconds": 13,
102
+ "seconds_per_chunk": 2,
103
+ "text_config": {
104
+ "_name_or_path": "",
105
+ "add_cross_attention": false,
106
+ "architectures": null,
107
+ "attention_bias": false,
108
+ "attention_dropout": 0.0,
109
+ "bad_words_ids": null,
110
+ "begin_suppress_tokens": null,
111
+ "bos_token_id": null,
112
+ "chunk_size_feed_forward": 0,
113
+ "cross_attention_hidden_size": null,
114
+ "decoder_sparse_step": 1,
115
+ "decoder_start_token_id": null,
116
+ "diversity_penalty": 0.0,
117
+ "do_sample": false,
118
+ "dtype": null,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "head_dim": 128,
127
+ "hidden_act": "silu",
128
+ "hidden_size": 2048,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "initializer_range": 0.02,
134
+ "intermediate_size": 768,
135
+ "is_decoder": false,
136
+ "is_encoder_decoder": false,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "length_penalty": 1.0,
142
+ "max_length": 20,
143
+ "max_position_embeddings": 65536,
144
+ "min_length": 0,
145
+ "mlp_only_layers": [],
146
+ "model_type": "qwen3_omni_moe_text",
147
+ "moe_intermediate_size": 768,
148
+ "no_repeat_ngram_size": 0,
149
+ "norm_topk_prob": true,
150
+ "num_attention_heads": 32,
151
+ "num_beam_groups": 1,
152
+ "num_beams": 1,
153
+ "num_experts": 128,
154
+ "num_experts_per_tok": 8,
155
+ "num_hidden_layers": 48,
156
+ "num_key_value_heads": 4,
157
+ "num_return_sequences": 1,
158
+ "output_attentions": false,
159
+ "output_hidden_states": false,
160
+ "output_router_logits": false,
161
+ "output_scores": false,
162
+ "pad_token_id": null,
163
+ "prefix": null,
164
+ "problem_type": null,
165
+ "pruned_heads": {},
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "rms_norm_eps": 1e-06,
171
+ "rope_scaling": {
172
+ "interleaved": true,
173
+ "mrope_section": [
174
+ 24,
175
+ 20,
176
+ 20
177
+ ],
178
+ "rope_type": "default",
179
+ "type": "default"
180
+ },
181
+ "rope_theta": 1000000,
182
+ "router_aux_loss_coef": 0.001,
183
+ "sep_token_id": null,
184
+ "shared_expert_intermediate_size": 0,
185
+ "sliding_window": null,
186
+ "suppress_tokens": null,
187
+ "task_specific_params": null,
188
+ "temperature": 1.0,
189
+ "tf_legacy_loss": false,
190
+ "tie_encoder_decoder": false,
191
+ "tie_word_embeddings": false,
192
+ "tokenizer_class": null,
193
+ "top_k": 50,
194
+ "top_p": 1.0,
195
+ "torchscript": false,
196
+ "typical_p": 1.0,
197
+ "use_bfloat16": false,
198
+ "use_cache": true,
199
+ "use_qk_norm": true,
200
+ "use_sliding_window": false,
201
+ "vocab_size": 152064
202
+ },
203
+ "user_token_id": 872,
204
+ "video_token_id": 151656,
205
+ "vision_config": {
206
+ "_name_or_path": "",
207
+ "add_cross_attention": false,
208
+ "apply_vit_abs_pos_embed": true,
209
+ "architectures": null,
210
+ "bad_words_ids": null,
211
+ "begin_suppress_tokens": null,
212
+ "bos_token_id": null,
213
+ "chunk_size_feed_forward": 0,
214
+ "cross_attention_hidden_size": null,
215
+ "decoder_start_token_id": null,
216
+ "deepstack_visual_indexes": [
217
+ 8,
218
+ 16,
219
+ 24
220
+ ],
221
+ "depth": 27,
222
+ "diversity_penalty": 0.0,
223
+ "do_sample": false,
224
+ "dtype": null,
225
+ "early_stopping": false,
226
+ "encoder_no_repeat_ngram_size": 0,
227
+ "eos_token_id": null,
228
+ "exponential_decay_length_penalty": null,
229
+ "finetuning_task": null,
230
+ "forced_bos_token_id": null,
231
+ "forced_eos_token_id": null,
232
+ "hidden_act": "gelu_pytorch_tanh",
233
+ "hidden_size": 1152,
234
+ "id2label": {
235
+ "0": "LABEL_0",
236
+ "1": "LABEL_1"
237
+ },
238
+ "image_size": 768,
239
+ "in_channels": 3,
240
+ "in_chans": 3,
241
+ "initializer_range": 0.02,
242
+ "intermediate_size": 4304,
243
+ "is_decoder": false,
244
+ "is_encoder_decoder": false,
245
+ "label2id": {
246
+ "LABEL_0": 0,
247
+ "LABEL_1": 1
248
+ },
249
+ "length_penalty": 1.0,
250
+ "max_length": 20,
251
+ "min_length": 0,
252
+ "model_type": "qwen3_omni_moe_vision_encoder",
253
+ "no_repeat_ngram_size": 0,
254
+ "num_beam_groups": 1,
255
+ "num_beams": 1,
256
+ "num_heads": 16,
257
+ "num_return_sequences": 1,
258
+ "out_hidden_size": 2048,
259
+ "output_attentions": false,
260
+ "output_hidden_states": false,
261
+ "output_scores": false,
262
+ "pad_token_id": null,
263
+ "patch_size": 16,
264
+ "prefix": null,
265
+ "problem_type": null,
266
+ "pruned_heads": {},
267
+ "remove_invalid_values": false,
268
+ "repetition_penalty": 1.0,
269
+ "return_dict": true,
270
+ "return_dict_in_generate": false,
271
+ "sep_token_id": null,
272
+ "spatial_merge_size": 2,
273
+ "spatial_patch_size": 16,
274
+ "suppress_tokens": null,
275
+ "task_specific_params": null,
276
+ "temperature": 1.0,
277
+ "temporal_patch_size": 2,
278
+ "tf_legacy_loss": false,
279
+ "tie_encoder_decoder": false,
280
+ "tie_word_embeddings": true,
281
+ "tokenizer_class": null,
282
+ "tokens_per_second": 2,
283
+ "top_k": 50,
284
+ "top_p": 1.0,
285
+ "torchscript": false,
286
+ "typical_p": 1.0,
287
+ "use_bfloat16": false
288
+ },
289
+ "vision_end_token_id": 151653,
290
+ "vision_start_token_id": 151652
291
+ },
292
+ "transformers_version": "4.57.0.dev0",
293
+ "tts_bos_token_id": 151672,
294
+ "tts_eos_token_id": 151673,
295
+ "tts_pad_token_id": 151671,
296
+ "user_token_id": 872
297
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_new_tokens": 32768,
3
+ "repetition_penalty": 1.0,
4
+ "temperature": 0.6,
5
+ "top_k": 20,
6
+ "top_p": 0.95
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2e8477f5e8aef9163d7b46ead3e955bf13fec2826092990bc1df434cba67af
3
+ size 3999958720
model-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eea7a21447ac311636eeb8b2a8f4a10fbe8e1dbb85870432081a0785715c820
3
+ size 3999984304
model-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95465568b11da26b96dbf873c785baec9b371b07d1eaee7516bf0b97ca4d8b8d
3
+ size 3997370920
model-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b237e045ab59f8038c8b31fb2d311ef3063101adf90656f1ab931f6c082f87
3
+ size 3999985128
model-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7c8c1000c27533a7a1142f6249119539e39964056d67f1bbc889c56e7b7365
3
+ size 3999985488
model-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f292ccd339bb83d5282ea8d941a77d7a8a8e12ba721a711b6691a2e9156cdbd
3
+ size 3999985560
model-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628f156bc9f4bfa57095dd91b21e2fdf16856d67d249eeb722915f40e1821e8d
3
+ size 3999985584
model-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461eeda21222c8f69c4bc7ebc6e977ad776f7350f92c0b440de9149b1452b27c
3
+ size 3997372144
model-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e7baf316bbfbf5ca007847402f9435ce985bb2893e25e33bd9bb7972aee3f3
3
+ size 3999985488
model-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8bd10a2f8d6c5c504f50ec6a1bfbfb311757ce226e600775ac6511c6589bbb
3
+ size 3999985504
model-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86e1441bdc73585b1e958535aa58a39c96b60ffb1a4af88bdb344df8b678ac8
3
+ size 3999985560
model-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ae0c5e0073778cc6ac487e8056d803696aa9045738e7e9339e1197b37ba0f7
3
+ size 3987402152
model-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d775cad42794687b663d5c574b2ec851035e1a8fda81a61f9bec7dfb84cc86
3
+ size 3997372112
model-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3195c7dda8c4f6033f5f2bc002d06e2f6eb8fad38fe73e92fe798715f42d03e
3
+ size 3999985488
model-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5049b50cfd5ef272dca6473b2451774a8828a93aeb37beaadbbe6b4c1f2e41
3
+ size 3999985520
model-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe9823d6d7edf67788970f1f9336cf88cf908dd62bdc26692795dbb4488bebe
3
+ size 3461668112
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dither": 0.0,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "n_fft": 400,
21
+ "n_samples": 4800000,
22
+ "nb_max_frames": 30000,
23
+ "padding_side": "right",
24
+ "padding_value": 0.0,
25
+ "patch_size": 16,
26
+ "processor_class": "Qwen3OmniMoeProcessor",
27
+ "return_attention_mask": true,
28
+ "sampling_rate": 16000,
29
+ "temporal_patch_size": 2
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151669": {
214
+ "content": "<|audio_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|audio_end|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<tts_pad>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tts_text_bos>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<tts_text_eod>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<tts_text_bos_single>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|audio_pad|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ }
269
+ },
270
+ "additional_special_tokens": [
271
+ "<|im_start|>",
272
+ "<|im_end|>",
273
+ "<|object_ref_start|>",
274
+ "<|object_ref_end|>",
275
+ "<|box_start|>",
276
+ "<|box_end|>",
277
+ "<|quad_start|>",
278
+ "<|quad_end|>",
279
+ "<|vision_start|>",
280
+ "<|vision_end|>",
281
+ "<|vision_pad|>",
282
+ "<|image_pad|>",
283
+ "<|video_pad|>",
284
+ "<|audio_start|>",
285
+ "<|audio_end|>",
286
+ "<tts_pad>",
287
+ "<tts_text_bos>",
288
+ "<tts_text_bos_single>",
289
+ "<|audio_pad|>"
290
+ ],
291
+ "extra_special_tokens": {
292
+ "image_token": "<|image_pad|>",
293
+ "audio_token": "<|audio_pad|>",
294
+ "video_token": "<|video_pad|>",
295
+ "vision_bos_token": "<|vision_start|>",
296
+ "vision_eos_token": "<|vision_end|>",
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>"
299
+ },
300
+ "bos_token": null,
301
+ "clean_up_tokenization_spaces": false,
302
+ "eos_token": "<|im_end|>",
303
+ "errors": "replace",
304
+ "model_max_length": 131072,
305
+ "pad_token": "<|endoftext|>",
306
+ "split_special_tokens": false,
307
+ "tokenizer_class": "Qwen2Tokenizer",
308
+ "unk_token": null,
309
+ "image_token": "<|image_pad|>",
310
+ "audio_token": "<|audio_pad|>",
311
+ "video_token": "<|video_pad|>",
312
+ "vision_bos_token": "<|vision_start|>",
313
+ "vision_eos_token": "<|vision_end|>",
314
+ "audio_bos_token": "<|audio_start|>",
315
+ "audio_eos_token": "<|audio_end|>"
316
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff