Hugging Face's logo

ASLP-lab
/
FM-Speech

Audio Classification
Safetensors
qwen3_omni_moe
Model card Files
xet
 Community
1
ASLP-lab commited on
Commit
99e638b
·
verified ·
1 Parent(s): a9d2dde

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +35 -0
  3. chat_template.jinja +122 -0
  4. config.json +564 -0
  5. merges.txt +0 -0
  6. model-00001-of-00015.safetensors +3 -0
  7. model-00002-of-00015.safetensors +3 -0
  8. model-00003-of-00015.safetensors +3 -0
  9. model-00004-of-00015.safetensors +3 -0
  10. model-00005-of-00015.safetensors +3 -0
  11. model-00006-of-00015.safetensors +3 -0
  12. model-00007-of-00015.safetensors +3 -0
  13. model-00008-of-00015.safetensors +3 -0
  14. model-00009-of-00015.safetensors +3 -0
  15. model-00010-of-00015.safetensors +3 -0
  16. model-00011-of-00015.safetensors +3 -0
  17. model-00012-of-00015.safetensors +3 -0
  18. model-00013-of-00015.safetensors +3 -0
  19. model-00014-of-00015.safetensors +3 -0
  20. model-00015-of-00015.safetensors +3 -0
  21. model.safetensors.index.json +0 -0
  22. preprocessor_config.json +31 -0
  23. special_tokens_map.json +44 -0
  24. tokenizer.json +3 -0
  25. tokenizer_config.json +317 -0
  26. video_preprocessor_config.json +55 -0
  27. vocab.json +0 -0
.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
added_tokens.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<tts_pad>": 151671,
9
+ "<tts_text_bos>": 151672,
10
+ "<tts_text_bos_single>": 151674,
11
+ "<tts_text_eod>": 151673,
12
+ "<|audio_end|>": 151670,
13
+ "<|audio_pad|>": 151675,
14
+ "<|audio_start|>": 151669,
15
+ "<|box_end|>": 151649,
16
+ "<|box_start|>": 151648,
17
+ "<|endoftext|>": 151643,
18
+ "<|file_sep|>": 151664,
19
+ "<|fim_middle|>": 151660,
20
+ "<|fim_pad|>": 151662,
21
+ "<|fim_prefix|>": 151659,
22
+ "<|fim_suffix|>": 151661,
23
+ "<|im_end|>": 151645,
24
+ "<|im_start|>": 151644,
25
+ "<|image_pad|>": 151655,
26
+ "<|object_ref_end|>": 151647,
27
+ "<|object_ref_start|>": 151646,
28
+ "<|quad_end|>": 151651,
29
+ "<|quad_start|>": 151650,
30
+ "<|repo_name|>": 151663,
31
+ "<|video_pad|>": 151656,
32
+ "<|vision_end|>": 151653,
33
+ "<|vision_pad|>": 151654,
34
+ "<|vision_start|>": 151652
35
+ }
chat_template.jinja ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 content.type == 'image' or 'image' in content or 'image_url' in content %}
9
+ {{- "<|vision_start|><|image_pad|><|vision_end|>" }}
10
+ {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
11
+ {{- "<|audio_start|><|audio_pad|><|audio_end|>" }}
12
+ {%- elif content.type == 'video' or 'video' in content %}
13
+ {{- "<|vision_start|><|video_pad|><|vision_end|>" }}
14
+ {%- elif content.type == 'text' %}
15
+ {{- content.text }}
16
+ {%- endif %}
17
+ {%- endfor %}
18
+ {%- endif %}
19
+ {%- endif %}
20
+ {{- '\n\n' }}
21
+ {{- "# 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>" }}
22
+ {%- for tool in tools %}
23
+ {{- "\n" }}
24
+ {{- tool | tojson }}
25
+ {%- endfor %}
26
+ {{- "\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" }}
27
+ {%- else %}
28
+ {%- if messages[0].role == 'system' %}
29
+ {%- if messages[0].content is string %}
30
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
31
+ {%- else %}
32
+ {%- for content in messages[0].content %}
33
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
34
+ {{- '<|im_start|>system\n' +"<|vision_start|><|image_pad|><|vision_end|>"+ '<|im_end|>\n' }}
35
+ {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}
36
+ {{- '<|im_start|>system\n' +"<|audio_start|><|audio_pad|><|audio_end|>"+ '<|im_end|>\n' }}
37
+ {%- elif content.type == 'video' or 'video' in content %}
38
+ {{- '<|im_start|>system\n' +"<|vision_start|><|video_pad|><|vision_end|>"+ '<|im_end|>\n' }}
39
+ {%- elif content.type == 'text' %}
40
+ {{- '<|im_start|>system\n' +content.text+ '<|im_end|>\n' }}
41
+ {%- endif %}
42
+ {%- endfor %}
43
+ {%- endif %}
44
+ {%- endif %}
45
+ {%- endif %}
46
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
47
+ {%- for message in messages[::-1] %}
48
+ {%- set index = (messages|length - 1) - loop.index0 %}
49
+ {%- 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>')) %}
50
+ {%- set ns.multi_step_tool = false %}
51
+ {%- set ns.last_query_index = index %}
52
+ {%- endif %}
53
+ {%- endfor %}
54
+ {%- for message in messages %}
55
+ {%- if message.content is string %}
56
+ {%- set content = message.content %}
57
+ {%- else %}
58
+ {%- set content = namespace(text="") %}
59
+ {%- for mcontent in message.content %}
60
+ {%- if mcontent.type == 'image' or 'image' in mcontent or 'image_url' in mcontent %}
61
+ {%- set content.text = content.text~"<|vision_start|><|image_pad|><|vision_end|>" %}
62
+ {%- elif mcontent.type == 'audio' or 'audio' in mcontent or 'audio_url' in mcontent %}
63
+ {%- set content.text = content.text~"<|audio_start|><|audio_pad|><|audio_end|>" %}
64
+ {%- elif mcontent.type == 'video' or 'video' in mcontent %}
65
+ {%- set content.text = content.text~"<|vision_start|><|video_pad|><|vision_end|>" %}
66
+ {%- elif mcontent.type == 'text' %}
67
+ {%- set content.text = content.text~mcontent.text %}
68
+ {%- endif %}
69
+ {%- endfor %}
70
+ {%- set content = content.text %}
71
+ {%- endif %}
72
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
73
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
74
+ {%- elif message.role == "assistant" %}
75
+ {%- set reasoning_content = "" %}
76
+ {%- if message.reasoning_content is string %}
77
+ {%- set reasoning_content = message.reasoning_content %}
78
+ {%- else %}
79
+ {%- if '</think>' in content %}
80
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
81
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
82
+ {%- endif %}
83
+ {%- endif %}
84
+ {%- if loop.index0 > ns.last_query_index %}
85
+ {%- if loop.last or (not loop.last and reasoning_content) %}
86
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip("\n") + '\n</think>\n\n' + content.lstrip('\n') }}
87
+ {%- else %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content }}
89
+ {%- endif %}
90
+ {%- else %}
91
+ {{- '<|im_start|>' + message.role + '\n' + content }}
92
+ {%- endif %}
93
+ {%- if message.tool_calls %}
94
+ {%- for tool_call in message.tool_calls %}
95
+ {%- if (loop.first and content) or (not loop.first) %}{{- '\n' }}{%- endif %}
96
+ {%- if tool_call.function %}
97
+ {%- set tool_call = tool_call.function %}
98
+ {%- endif %}
99
+ {{- '<tool_call>\n{"name": "' }}
100
+ {{- tool_call.name }}
101
+ {{- '", "arguments": ' }}
102
+ {%- if tool_call.arguments is string %}
103
+ {{- tool_call.arguments }}
104
+ {%- else %}
105
+ {{- tool_call.arguments | tojson }}
106
+ {%- endif %}
107
+ {{- '}\n</tool_call>' }}
108
+ {%- endfor %}
109
+ {%- endif %}
110
+ {{- '<|im_end|>\n' }}
111
+ {%- elif message.role == "tool" %}
112
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}
113
+ {{- '\n<tool_response>\n' }}
114
+ {{- content }}
115
+ {{- '\n</tool_response>' }}
116
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
117
+ {%- endif %}
118
+ {%- endfor %}
119
+ {%- if add_generation_prompt %}
120
+ {{- '<|im_start|>assistant\n' }}
121
+ {%- if enable_thinking is defined and enable_thinking is false %}{{- '<think>\n\n</think>\n\n' }}{%- endif %}
122
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3OmniMoeForConditionalGeneration"
4
+ ],
5
+ "assistant_token_id": 77091,
6
+ "code2wav_config": {
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "codebook_dim": 512,
10
+ "codebook_size": 2048,
11
+ "decoder_dim": 1536,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "intermediate_size": 3072,
15
+ "layer_scale_initial_scale": 0.01,
16
+ "max_position_embeddings": 8000,
17
+ "model_type": "",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 8,
20
+ "num_key_value_heads": 16,
21
+ "num_quantizers": 16,
22
+ "num_semantic_quantizers": 1,
23
+ "pad_token_id": 151643,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_theta": 10000,
26
+ "semantic_codebook_size": 4096,
27
+ "sliding_window": 72,
28
+ "upsample_rates": [
29
+ 8,
30
+ 5,
31
+ 4,
32
+ 3
33
+ ],
34
+ "upsampling_ratios": [
35
+ 2,
36
+ 2
37
+ ],
38
+ "vector_quantization_hidden_dimension": 512
39
+ },
40
+ "dtype": "bfloat16",
41
+ "enable_audio_output": true,
42
+ "hidden_size": 1024,
43
+ "im_end_token_id": 151645,
44
+ "im_start_token_id": 151644,
45
+ "keys_to_ignore_at_inference": [
46
+ "past_key_values",
47
+ "hidden_states",
48
+ "attention_mask",
49
+ "hidden_states",
50
+ "attention_mask",
51
+ "hidden_states",
52
+ "attention_mask",
53
+ "hidden_states",
54
+ "attention_mask"
55
+ ],
56
+ "model_type": "qwen3_omni_moe",
57
+ "pad_token_id": 151643,
58
+ "system_token_id": 8948,
59
+ "talker_config": {
60
+ "accept_hidden_layer": 24,
61
+ "audio_end_token_id": 151670,
62
+ "audio_start_token_id": 151669,
63
+ "audio_token_id": 151675,
64
+ "code_predictor_config": {
65
+ "_name_or_path": "",
66
+ "add_cross_attention": false,
67
+ "architectures": null,
68
+ "attention_bias": false,
69
+ "attention_dropout": 0,
70
+ "bad_words_ids": null,
71
+ "begin_suppress_tokens": null,
72
+ "bos_token_id": null,
73
+ "chunk_size_feed_forward": 0,
74
+ "cross_attention_hidden_size": null,
75
+ "decoder_start_token_id": null,
76
+ "diversity_penalty": 0.0,
77
+ "do_sample": false,
78
+ "dtype": null,
79
+ "early_stopping": false,
80
+ "encoder_no_repeat_ngram_size": 0,
81
+ "eos_token_id": null,
82
+ "exponential_decay_length_penalty": null,
83
+ "finetuning_task": null,
84
+ "forced_bos_token_id": null,
85
+ "forced_eos_token_id": null,
86
+ "head_dim": 128,
87
+ "hidden_act": "silu",
88
+ "hidden_size": 1024,
89
+ "id2label": {
90
+ "0": "LABEL_0",
91
+ "1": "LABEL_1"
92
+ },
93
+ "initializer_range": 0.02,
94
+ "intermediate_size": 3072,
95
+ "is_decoder": false,
96
+ "is_encoder_decoder": false,
97
+ "label2id": {
98
+ "LABEL_0": 0,
99
+ "LABEL_1": 1
100
+ },
101
+ "layer_types": [
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention"
107
+ ],
108
+ "length_penalty": 1.0,
109
+ "max_length": 20,
110
+ "max_position_embeddings": 32768,
111
+ "max_window_layers": 28,
112
+ "min_length": 0,
113
+ "model_type": "qwen3_omni_moe_talker_code_predictor",
114
+ "no_repeat_ngram_size": 0,
115
+ "num_attention_heads": 16,
116
+ "num_beam_groups": 1,
117
+ "num_beams": 1,
118
+ "num_code_groups": 16,
119
+ "num_hidden_layers": 5,
120
+ "num_key_value_heads": 8,
121
+ "num_return_sequences": 1,
122
+ "output_attentions": false,
123
+ "output_hidden_states": false,
124
+ "output_scores": false,
125
+ "pad_token_id": 151643,
126
+ "prefix": null,
127
+ "problem_type": null,
128
+ "pruned_heads": {},
129
+ "remove_invalid_values": false,
130
+ "repetition_penalty": 1.0,
131
+ "return_dict": true,
132
+ "return_dict_in_generate": false,
133
+ "rms_norm_eps": 1e-06,
134
+ "rope_scaling": null,
135
+ "rope_theta": 1000000,
136
+ "sep_token_id": null,
137
+ "sliding_window": null,
138
+ "suppress_tokens": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tf_legacy_loss": false,
142
+ "tie_encoder_decoder": false,
143
+ "tie_word_embeddings": false,
144
+ "tokenizer_class": null,
145
+ "top_k": 50,
146
+ "top_p": 1.0,
147
+ "torchscript": false,
148
+ "typical_p": 1.0,
149
+ "use_bfloat16": false,
150
+ "use_cache": true,
151
+ "use_sliding_window": false,
152
+ "vocab_size": 2048
153
+ },
154
+ "codec_bos_id": 2149,
155
+ "codec_eos_token_id": 2150,
156
+ "codec_nothink_id": 2155,
157
+ "codec_pad_id": 2148,
158
+ "codec_think_bos_id": 2156,
159
+ "codec_think_eos_id": 2157,
160
+ "image_token_id": 151655,
161
+ "model_type": "",
162
+ "num_code_groups": 16,
163
+ "output_router_logits": false,
164
+ "position_id_per_seconds": 13,
165
+ "seconds_per_chunk": 2,
166
+ "spatial_merge_size": 2,
167
+ "speaker_id": {
168
+ "aiden": 2303,
169
+ "chelsie": 2301,
170
+ "ethan": 2302
171
+ },
172
+ "text_config": {
173
+ "_name_or_path": "",
174
+ "add_cross_attention": false,
175
+ "architectures": null,
176
+ "attention_bias": false,
177
+ "attention_dropout": 0,
178
+ "bad_words_ids": null,
179
+ "begin_suppress_tokens": null,
180
+ "bos_token_id": null,
181
+ "chunk_size_feed_forward": 0,
182
+ "cross_attention_hidden_size": null,
183
+ "decoder_sparse_step": 1,
184
+ "decoder_start_token_id": null,
185
+ "diversity_penalty": 0.0,
186
+ "do_sample": false,
187
+ "dtype": "bfloat16",
188
+ "early_stopping": false,
189
+ "encoder_no_repeat_ngram_size": 0,
190
+ "eos_token_id": null,
191
+ "exponential_decay_length_penalty": null,
192
+ "finetuning_task": null,
193
+ "forced_bos_token_id": null,
194
+ "forced_eos_token_id": null,
195
+ "head_dim": 128,
196
+ "hidden_act": "silu",
197
+ "hidden_size": 1024,
198
+ "id2label": {
199
+ "0": "LABEL_0",
200
+ "1": "LABEL_1"
201
+ },
202
+ "initializer_range": 0.02,
203
+ "intermediate_size": 2048,
204
+ "is_decoder": false,
205
+ "is_encoder_decoder": false,
206
+ "label2id": {
207
+ "LABEL_0": 0,
208
+ "LABEL_1": 1
209
+ },
210
+ "length_penalty": 1.0,
211
+ "max_length": 20,
212
+ "max_position_embeddings": 65536,
213
+ "min_length": 0,
214
+ "mlp_only_layers": [],
215
+ "model_type": "qwen3_omni_moe_talker_text",
216
+ "moe_intermediate_size": 384,
217
+ "no_repeat_ngram_size": 0,
218
+ "norm_topk_prob": true,
219
+ "num_attention_heads": 16,
220
+ "num_beam_groups": 1,
221
+ "num_beams": 1,
222
+ "num_experts": 128,
223
+ "num_experts_per_tok": 6,
224
+ "num_hidden_layers": 20,
225
+ "num_key_value_heads": 2,
226
+ "num_return_sequences": 1,
227
+ "output_attentions": false,
228
+ "output_hidden_states": false,
229
+ "output_router_logits": false,
230
+ "output_scores": false,
231
+ "pad_token_id": 151643,
232
+ "prefix": null,
233
+ "problem_type": null,
234
+ "pruned_heads": {},
235
+ "remove_invalid_values": false,
236
+ "repetition_penalty": 1.0,
237
+ "return_dict": true,
238
+ "return_dict_in_generate": false,
239
+ "rms_norm_eps": 1e-06,
240
+ "rope_scaling": {
241
+ "interleaved": true,
242
+ "mrope_section": [
243
+ 24,
244
+ 20,
245
+ 20
246
+ ],
247
+ "rope_type": "default",
248
+ "type": "default"
249
+ },
250
+ "rope_theta": 1000000,
251
+ "router_aux_loss_coef": 0.001,
252
+ "sep_token_id": null,
253
+ "shared_expert_intermediate_size": 768,
254
+ "sliding_window": null,
255
+ "suppress_tokens": null,
256
+ "task_specific_params": null,
257
+ "temperature": 1.0,
258
+ "tf_legacy_loss": false,
259
+ "tie_encoder_decoder": false,
260
+ "tie_word_embeddings": false,
261
+ "tokenizer_class": null,
262
+ "top_k": 50,
263
+ "top_p": 1.0,
264
+ "torchscript": false,
265
+ "typical_p": 1.0,
266
+ "use_bfloat16": false,
267
+ "use_cache": true,
268
+ "use_sliding_window": false,
269
+ "vocab_size": 3072
270
+ },
271
+ "thinker_hidden_size": 2048,
272
+ "video_token_id": 151656,
273
+ "vision_start_token_id": 151652
274
+ },
275
+ "thinker_config": {
276
+ "audio_config": {
277
+ "_name_or_path": "",
278
+ "activation_dropout": 0,
279
+ "activation_function": "gelu",
280
+ "add_cross_attention": false,
281
+ "architectures": null,
282
+ "attention_dropout": 0,
283
+ "bad_words_ids": null,
284
+ "begin_suppress_tokens": null,
285
+ "bos_token_id": null,
286
+ "chunk_size_feed_forward": 0,
287
+ "conv_chunksize": 500,
288
+ "cross_attention_hidden_size": null,
289
+ "d_model": 1280,
290
+ "decoder_start_token_id": null,
291
+ "diversity_penalty": 0.0,
292
+ "do_sample": false,
293
+ "downsample_hidden_size": 480,
294
+ "dropout": 0,
295
+ "dtype": "bfloat16",
296
+ "early_stopping": false,
297
+ "encoder_attention_heads": 20,
298
+ "encoder_ffn_dim": 5120,
299
+ "encoder_layers": 32,
300
+ "encoder_no_repeat_ngram_size": 0,
301
+ "eos_token_id": null,
302
+ "exponential_decay_length_penalty": null,
303
+ "finetuning_task": null,
304
+ "forced_bos_token_id": null,
305
+ "forced_eos_token_id": null,
306
+ "id2label": {
307
+ "0": "LABEL_0",
308
+ "1": "LABEL_1"
309
+ },
310
+ "initializer_range": 0.02,
311
+ "is_decoder": false,
312
+ "is_encoder_decoder": false,
313
+ "label2id": {
314
+ "LABEL_0": 0,
315
+ "LABEL_1": 1
316
+ },
317
+ "length_penalty": 1.0,
318
+ "max_length": 20,
319
+ "max_source_positions": 1500,
320
+ "min_length": 0,
321
+ "model_type": "qwen3_omni_moe_audio_encoder",
322
+ "n_window": 50,
323
+ "n_window_infer": 800,
324
+ "no_repeat_ngram_size": 0,
325
+ "num_beam_groups": 1,
326
+ "num_beams": 1,
327
+ "num_hidden_layers": 32,
328
+ "num_mel_bins": 128,
329
+ "num_return_sequences": 1,
330
+ "output_attentions": false,
331
+ "output_dim": 2048,
332
+ "output_hidden_states": false,
333
+ "output_scores": false,
334
+ "pad_token_id": 151643,
335
+ "prefix": null,
336
+ "problem_type": null,
337
+ "pruned_heads": {},
338
+ "remove_invalid_values": false,
339
+ "repetition_penalty": 1.0,
340
+ "return_dict": true,
341
+ "return_dict_in_generate": false,
342
+ "scale_embedding": false,
343
+ "sep_token_id": null,
344
+ "suppress_tokens": null,
345
+ "task_specific_params": null,
346
+ "temperature": 1.0,
347
+ "tf_legacy_loss": false,
348
+ "tie_encoder_decoder": false,
349
+ "tie_word_embeddings": true,
350
+ "tokenizer_class": null,
351
+ "top_k": 50,
352
+ "top_p": 1.0,
353
+ "torchscript": false,
354
+ "typical_p": 1.0,
355
+ "use_bfloat16": false
356
+ },
357
+ "audio_end_token_id": 151670,
358
+ "audio_start_token_id": 151669,
359
+ "audio_token_id": 151675,
360
+ "dtype": "bfloat16",
361
+ "image_token_id": 151655,
362
+ "initializer_range": 0.02,
363
+ "model_type": "qwen3_omni_moe_thinker",
364
+ "pad_token_id": 151643,
365
+ "position_id_per_seconds": 13,
366
+ "seconds_per_chunk": 2,
367
+ "text_config": {
368
+ "_name_or_path": "",
369
+ "add_cross_attention": false,
370
+ "architectures": null,
371
+ "attention_bias": false,
372
+ "attention_dropout": 0.0,
373
+ "bad_words_ids": null,
374
+ "begin_suppress_tokens": null,
375
+ "bos_token_id": null,
376
+ "chunk_size_feed_forward": 0,
377
+ "cross_attention_hidden_size": null,
378
+ "decoder_sparse_step": 1,
379
+ "decoder_start_token_id": null,
380
+ "diversity_penalty": 0.0,
381
+ "do_sample": false,
382
+ "dtype": "bfloat16",
383
+ "early_stopping": false,
384
+ "encoder_no_repeat_ngram_size": 0,
385
+ "eos_token_id": null,
386
+ "exponential_decay_length_penalty": null,
387
+ "finetuning_task": null,
388
+ "forced_bos_token_id": null,
389
+ "forced_eos_token_id": null,
390
+ "head_dim": 128,
391
+ "hidden_act": "silu",
392
+ "hidden_size": 2048,
393
+ "id2label": {
394
+ "0": "LABEL_0",
395
+ "1": "LABEL_1"
396
+ },
397
+ "initializer_range": 0.02,
398
+ "intermediate_size": 768,
399
+ "is_decoder": false,
400
+ "is_encoder_decoder": false,
401
+ "label2id": {
402
+ "LABEL_0": 0,
403
+ "LABEL_1": 1
404
+ },
405
+ "length_penalty": 1.0,
406
+ "max_length": 20,
407
+ "max_position_embeddings": 65536,
408
+ "min_length": 0,
409
+ "mlp_only_layers": [],
410
+ "model_type": "qwen3_omni_moe_text",
411
+ "moe_intermediate_size": 768,
412
+ "no_repeat_ngram_size": 0,
413
+ "norm_topk_prob": true,
414
+ "num_attention_heads": 32,
415
+ "num_beam_groups": 1,
416
+ "num_beams": 1,
417
+ "num_experts": 128,
418
+ "num_experts_per_tok": 8,
419
+ "num_hidden_layers": 48,
420
+ "num_key_value_heads": 4,
421
+ "num_return_sequences": 1,
422
+ "output_attentions": false,
423
+ "output_hidden_states": false,
424
+ "output_router_logits": false,
425
+ "output_scores": false,
426
+ "pad_token_id": 151643,
427
+ "prefix": null,
428
+ "problem_type": null,
429
+ "pruned_heads": {},
430
+ "remove_invalid_values": false,
431
+ "repetition_penalty": 1.0,
432
+ "return_dict": true,
433
+ "return_dict_in_generate": false,
434
+ "rms_norm_eps": 1e-06,
435
+ "rope_scaling": {
436
+ "interleaved": true,
437
+ "mrope_interleaved": true,
438
+ "mrope_section": [
439
+ 24,
440
+ 20,
441
+ 20
442
+ ],
443
+ "rope_type": "default",
444
+ "type": "default"
445
+ },
446
+ "rope_theta": 1000000,
447
+ "router_aux_loss_coef": 0.001,
448
+ "sep_token_id": null,
449
+ "shared_expert_intermediate_size": 0,
450
+ "sliding_window": null,
451
+ "suppress_tokens": null,
452
+ "task_specific_params": null,
453
+ "temperature": 1.0,
454
+ "tf_legacy_loss": false,
455
+ "tie_encoder_decoder": false,
456
+ "tie_word_embeddings": false,
457
+ "tokenizer_class": null,
458
+ "top_k": 50,
459
+ "top_p": 1.0,
460
+ "torchscript": false,
461
+ "typical_p": 1.0,
462
+ "use_bfloat16": false,
463
+ "use_cache": true,
464
+ "use_qk_norm": true,
465
+ "use_sliding_window": false,
466
+ "vocab_size": 152064
467
+ },
468
+ "user_token_id": 872,
469
+ "video_token_id": 151656,
470
+ "vision_config": {
471
+ "_name_or_path": "",
472
+ "add_cross_attention": false,
473
+ "apply_vit_abs_pos_embed": true,
474
+ "architectures": null,
475
+ "bad_words_ids": null,
476
+ "begin_suppress_tokens": null,
477
+ "bos_token_id": null,
478
+ "chunk_size_feed_forward": 0,
479
+ "cross_attention_hidden_size": null,
480
+ "decoder_start_token_id": null,
481
+ "deepstack_visual_indexes": [
482
+ 8,
483
+ 16,
484
+ 24
485
+ ],
486
+ "depth": 27,
487
+ "diversity_penalty": 0.0,
488
+ "do_sample": false,
489
+ "dtype": "bfloat16",
490
+ "early_stopping": false,
491
+ "encoder_no_repeat_ngram_size": 0,
492
+ "eos_token_id": null,
493
+ "exponential_decay_length_penalty": null,
494
+ "finetuning_task": null,
495
+ "forced_bos_token_id": null,
496
+ "forced_eos_token_id": null,
497
+ "hidden_act": "gelu_pytorch_tanh",
498
+ "hidden_size": 1152,
499
+ "id2label": {
500
+ "0": "LABEL_0",
501
+ "1": "LABEL_1"
502
+ },
503
+ "image_size": 768,
504
+ "in_channels": 3,
505
+ "in_chans": 3,
506
+ "initializer_range": 0.02,
507
+ "intermediate_size": 4304,
508
+ "is_decoder": false,
509
+ "is_encoder_decoder": false,
510
+ "label2id": {
511
+ "LABEL_0": 0,
512
+ "LABEL_1": 1
513
+ },
514
+ "length_penalty": 1.0,
515
+ "max_length": 20,
516
+ "min_length": 0,
517
+ "model_type": "qwen3_omni_moe_vision_encoder",
518
+ "no_repeat_ngram_size": 0,
519
+ "num_beam_groups": 1,
520
+ "num_beams": 1,
521
+ "num_heads": 16,
522
+ "num_position_embeddings": 2304,
523
+ "num_return_sequences": 1,
524
+ "out_hidden_size": 2048,
525
+ "output_attentions": false,
526
+ "output_hidden_states": false,
527
+ "output_scores": false,
528
+ "pad_token_id": 151643,
529
+ "patch_size": 16,
530
+ "prefix": null,
531
+ "problem_type": null,
532
+ "pruned_heads": {},
533
+ "remove_invalid_values": false,
534
+ "repetition_penalty": 1.0,
535
+ "return_dict": true,
536
+ "return_dict_in_generate": false,
537
+ "sep_token_id": null,
538
+ "spatial_merge_size": 2,
539
+ "spatial_patch_size": 16,
540
+ "suppress_tokens": null,
541
+ "task_specific_params": null,
542
+ "temperature": 1.0,
543
+ "temporal_patch_size": 2,
544
+ "tf_legacy_loss": false,
545
+ "tie_encoder_decoder": false,
546
+ "tie_word_embeddings": true,
547
+ "tokenizer_class": null,
548
+ "tokens_per_second": 2,
549
+ "top_k": 50,
550
+ "top_p": 1.0,
551
+ "torchscript": false,
552
+ "typical_p": 1.0,
553
+ "use_bfloat16": false
554
+ },
555
+ "vision_end_token_id": 151653,
556
+ "vision_start_token_id": 151652
557
+ },
558
+ "transformers_version": "4.57.3",
559
+ "tts_bos_token_id": 151672,
560
+ "tts_eos_token_id": 151673,
561
+ "tts_pad_token_id": 151671,
562
+ "user_token_id": 872,
563
+ "vocab_size": 152064
564
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0667c9f6d4134b747156b0dde26024f45ac1bf376b8904a3bce2cb0bb25f7e89
3
+ size 4999746336
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829fbbf28f51793ede999630d76ef2d60edf8bb1716b587b23bc5d50ef4040b0
3
+ size 4995907928
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c6ca2749d0c85f6cdec4b711a908ecab991b45ecda30b1fc585d337b0752525
3
+ size 4998681018
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0643761662441c82221a22d9aa2637e3e78ed74928439dcb23fd3653d2bbf3cb
3
+ size 4997754200
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03a669eaf801872dc74f44dc8b067f5420f74383d9168fbec5299aea03f64c6
3
+ size 4997754968
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02d1a1c8a5084358cc5e83e9db079191bc4c077b008b97dbd3c596dd26dd80d
3
+ size 4997755776
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d941f8a42195db7c1460aa3a72ee0066f56bff3bcfb55dc0344dd7fb8c9a7acb
3
+ size 4997755776
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca175f499a1f51f4a4fb2aaacc5b9cdff5e6790cbcd2b4c5e26b032342fcda91
3
+ size 4997755776
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b14ca9b57096993cb69e5e9f87e0003d5c939b641a071a1df813c2a7d12ad7f
3
+ size 4991468272
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9f0dbfdfa2a6f179561303b90bcb9926561c7c50e4cf468beedc70f4fd138f2
3
+ size 4985172320
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4e8a661e58c79f55210fa13bfbeb9bbb4d70f7e1fb81aea72771f1c59f3c95
3
+ size 4985172320
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c462927b28d2b38c4cde3a43af2be278b354c6e1b32decf12fcb7cd40ac6a6dc
3
+ size 4985172320
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26b06deb0025f9160350de4c4fb87e5a55398d79ac8b45a30c7370feb82a47d
3
+ size 4985172320
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d360220bc549a7a422f3cbec511c87559ba43ddb20d8a725ea11707f59b1b3eb
3
+ size 4985172320
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579b9cc9e356011fa47f83e0678edb9ab267eba2087539535de587aa1e24d277
3
+ size 622858440
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dither": 0.0,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "chunk_length": 300,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "max_pixels": 12845056,
19
+ "merge_size": 2,
20
+ "min_pixels": 3136,
21
+ "n_fft": 400,
22
+ "n_samples": 4800000,
23
+ "nb_max_frames": 30000,
24
+ "padding_side": "right",
25
+ "padding_value": 0.0,
26
+ "patch_size": 16,
27
+ "processor_class": "Qwen3OmniMoeProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<tts_pad>",
19
+ "<tts_text_bos>",
20
+ "<tts_text_bos_single>",
21
+ "<|audio_pad|>"
22
+ ],
23
+ "audio_bos_token": "<|audio_start|>",
24
+ "audio_eos_token": "<|audio_end|>",
25
+ "audio_token": "<|audio_pad|>",
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "image_token": "<|image_pad|>",
34
+ "pad_token": {
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "video_token": "<|video_pad|>",
42
+ "vision_bos_token": "<|vision_start|>",
43
+ "vision_eos_token": "<|vision_end|>"
44
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09267689b8362020b9763b65dd5be7e086b31e28d72e02837a9e781de9a91bc7
3
+ size 11423986
tokenizer_config.json ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "audio_bos_token": "<|audio_start|>",
292
+ "audio_eos_token": "<|audio_end|>",
293
+ "audio_token": "<|audio_pad|>",
294
+ "bos_token": null,
295
+ "clean_up_tokenization_spaces": false,
296
+ "eos_token": "<|im_end|>",
297
+ "errors": "replace",
298
+ "extra_special_tokens": {
299
+ "audio_bos_token": "<|audio_start|>",
300
+ "audio_eos_token": "<|audio_end|>",
301
+ "audio_token": "<|audio_pad|>",
302
+ "image_token": "<|image_pad|>",
303
+ "video_token": "<|video_pad|>",
304
+ "vision_bos_token": "<|vision_start|>",
305
+ "vision_eos_token": "<|vision_end|>"
306
+ },
307
+ "image_token": "<|image_pad|>",
308
+ "model_max_length": 131072,
309
+ "pad_token": "<|endoftext|>",
310
+ "processor_class": "Qwen3OmniMoeProcessor",
311
+ "split_special_tokens": false,
312
+ "tokenizer_class": "Qwen2Tokenizer",
313
+ "unk_token": null,
314
+ "video_token": "<|video_pad|>",
315
+ "vision_bos_token": "<|vision_start|>",
316
+ "vision_eos_token": "<|vision_end|>"
317
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "crop_size": null,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "dither": 0.0,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "do_sample_frames": false,
14
+ "feature_extractor_type": "WhisperFeatureExtractor",
15
+ "feature_size": 128,
16
+ "fps": null,
17
+ "hop_length": 160,
18
+ "image_mean": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "image_std": [
24
+ 0.5,
25
+ 0.5,
26
+ 0.5
27
+ ],
28
+ "input_data_format": null,
29
+ "max_frames": 768,
30
+ "max_pixels": 12845056,
31
+ "merge_size": 2,
32
+ "min_frames": 4,
33
+ "min_pixels": 3136,
34
+ "n_fft": 400,
35
+ "n_samples": 4800000,
36
+ "nb_max_frames": 30000,
37
+ "num_frames": null,
38
+ "pad_size": null,
39
+ "padding_side": "right",
40
+ "padding_value": 0.0,
41
+ "patch_size": 16,
42
+ "processor_class": "Qwen3OmniMoeProcessor",
43
+ "resample": 3,
44
+ "rescale_factor": 0.00392156862745098,
45
+ "return_attention_mask": true,
46
+ "return_metadata": false,
47
+ "sampling_rate": 16000,
48
+ "size": {
49
+ "longest_edge": 12845056,
50
+ "shortest_edge": 3136
51
+ },
52
+ "temporal_patch_size": 2,
53
+ "video_metadata": null,
54
+ "video_processor_type": "Qwen2VLVideoProcessor"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff