Hugging Face's logo

TheClusterDev
/
Q3OI-FP8

Safetensors
qwen3_omni_moe
compressed-tensors
Model card Files
xet
TheClusterDev commited on
Commit
7a8c2bc
·
verified ·
1 Parent(s): a82acb2

Compressed LLM

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +35 -0
  3. chat_template.jinja +122 -0
  4. config.json +595 -0
  5. generation_config.json +9 -0
  6. merges.txt +0 -0
  7. model.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. preprocessor_config.json +31 -0
  10. recipe.yaml +6 -0
  11. special_tokens_map.json +44 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +317 -0
  14. video_preprocessor_config.json +54 -0
  15. 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 +1,595 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 10000,
25
+ "semantic_codebook_size": 4096,
26
+ "sliding_window": 72,
27
+ "upsample_rates": [
28
+ 8,
29
+ 5,
30
+ 4,
31
+ 3
32
+ ],
33
+ "upsampling_ratios": [
34
+ 2,
35
+ 2
36
+ ],
37
+ "vector_quantization_hidden_dimension": 512
38
+ },
39
+ "dtype": "bfloat16",
40
+ "enable_audio_output": false,
41
+ "im_end_token_id": 151645,
42
+ "im_start_token_id": 151644,
43
+ "model_type": "qwen3_omni_moe",
44
+ "quantization_config": {
45
+ "format": "float-quantized",
46
+ "quant_method": "compressed-tensors",
47
+ "quantization_status": "compressed",
48
+ "version": "0.11.0",
49
+ "kv_cache_scheme": null,
50
+ "global_compression_ratio": null,
51
+ "transform_config": {},
52
+ "sparsity_config": {},
53
+ "config_groups": {
54
+ "group_0": {
55
+ "targets": [
56
+ "Linear"
57
+ ],
58
+ "input_activations": {
59
+ "type": "float",
60
+ "num_bits": 8,
61
+ "strategy": "token",
62
+ "symmetric": true,
63
+ "dynamic": true,
64
+ "observer": null,
65
+ "observer_kwargs": {},
66
+ "group_size": null,
67
+ "block_structure": null,
68
+ "actorder": null
69
+ },
70
+ "output_activations": null,
71
+ "weights": {
72
+ "type": "float",
73
+ "num_bits": 8,
74
+ "strategy": "channel",
75
+ "symmetric": true,
76
+ "dynamic": false,
77
+ "observer": "minmax",
78
+ "observer_kwargs": {},
79
+ "group_size": null,
80
+ "block_structure": null,
81
+ "actorder": null
82
+ }
83
+ }
84
+ },
85
+ "ignore": [
86
+ "lm_head",
87
+ "re:.*mlp.gate$",
88
+ "re:.*router$",
89
+ "re:.*shared_expert_gate$"
90
+ ]
91
+ },
92
+ "system_token_id": 8948,
93
+ "talker_config": {
94
+ "accept_hidden_layer": 24,
95
+ "audio_end_token_id": 151670,
96
+ "audio_start_token_id": 151669,
97
+ "audio_token_id": 151675,
98
+ "code_predictor_config": {
99
+ "_name_or_path": "",
100
+ "add_cross_attention": false,
101
+ "architectures": null,
102
+ "attention_bias": false,
103
+ "attention_dropout": 0,
104
+ "bad_words_ids": null,
105
+ "begin_suppress_tokens": null,
106
+ "bos_token_id": null,
107
+ "chunk_size_feed_forward": 0,
108
+ "cross_attention_hidden_size": null,
109
+ "decoder_start_token_id": null,
110
+ "diversity_penalty": 0.0,
111
+ "do_sample": false,
112
+ "dtype": null,
113
+ "early_stopping": false,
114
+ "encoder_no_repeat_ngram_size": 0,
115
+ "eos_token_id": null,
116
+ "exponential_decay_length_penalty": null,
117
+ "finetuning_task": null,
118
+ "forced_bos_token_id": null,
119
+ "forced_eos_token_id": null,
120
+ "head_dim": 128,
121
+ "hidden_act": "silu",
122
+ "hidden_size": 1024,
123
+ "id2label": {
124
+ "0": "LABEL_0",
125
+ "1": "LABEL_1"
126
+ },
127
+ "initializer_range": 0.02,
128
+ "intermediate_size": 3072,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_types": [
136
+ "full_attention",
137
+ "full_attention",
138
+ "full_attention",
139
+ "full_attention",
140
+ "full_attention"
141
+ ],
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "max_position_embeddings": 32768,
145
+ "max_window_layers": 28,
146
+ "min_length": 0,
147
+ "model_type": "qwen3_omni_moe_talker_code_predictor",
148
+ "no_repeat_ngram_size": 0,
149
+ "num_attention_heads": 16,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_code_groups": 16,
153
+ "num_hidden_layers": 5,
154
+ "num_key_value_heads": 8,
155
+ "num_return_sequences": 1,
156
+ "output_attentions": false,
157
+ "output_hidden_states": false,
158
+ "output_scores": false,
159
+ "pad_token_id": null,
160
+ "prefix": null,
161
+ "problem_type": null,
162
+ "pruned_heads": {},
163
+ "remove_invalid_values": false,
164
+ "repetition_penalty": 1.0,
165
+ "return_dict": true,
166
+ "return_dict_in_generate": false,
167
+ "rms_norm_eps": 1e-06,
168
+ "rope_scaling": null,
169
+ "rope_theta": 1000000,
170
+ "sep_token_id": null,
171
+ "sliding_window": null,
172
+ "suppress_tokens": null,
173
+ "task_specific_params": null,
174
+ "temperature": 1.0,
175
+ "tf_legacy_loss": false,
176
+ "tie_encoder_decoder": false,
177
+ "tie_word_embeddings": false,
178
+ "tokenizer_class": null,
179
+ "top_k": 50,
180
+ "top_p": 1.0,
181
+ "torchscript": false,
182
+ "typical_p": 1.0,
183
+ "use_bfloat16": false,
184
+ "use_cache": true,
185
+ "use_sliding_window": false,
186
+ "vocab_size": 2048
187
+ },
188
+ "codec_bos_id": 2149,
189
+ "codec_eos_token_id": 2150,
190
+ "codec_nothink_id": 2155,
191
+ "codec_pad_id": 2148,
192
+ "codec_think_bos_id": 2156,
193
+ "codec_think_eos_id": 2157,
194
+ "image_token_id": 151655,
195
+ "model_type": "",
196
+ "num_code_groups": 16,
197
+ "output_router_logits": false,
198
+ "position_id_per_seconds": 13,
199
+ "seconds_per_chunk": 2,
200
+ "spatial_merge_size": 2,
201
+ "speaker_id": {
202
+ "aiden": 2303,
203
+ "chelsie": 2301,
204
+ "ethan": 2302
205
+ },
206
+ "text_config": {
207
+ "_name_or_path": "",
208
+ "add_cross_attention": false,
209
+ "architectures": null,
210
+ "attention_bias": false,
211
+ "attention_dropout": 0,
212
+ "bad_words_ids": null,
213
+ "begin_suppress_tokens": null,
214
+ "bos_token_id": null,
215
+ "chunk_size_feed_forward": 0,
216
+ "cross_attention_hidden_size": null,
217
+ "decoder_sparse_step": 1,
218
+ "decoder_start_token_id": null,
219
+ "diversity_penalty": 0.0,
220
+ "do_sample": false,
221
+ "dtype": null,
222
+ "early_stopping": false,
223
+ "encoder_no_repeat_ngram_size": 0,
224
+ "eos_token_id": null,
225
+ "exponential_decay_length_penalty": null,
226
+ "finetuning_task": null,
227
+ "forced_bos_token_id": null,
228
+ "forced_eos_token_id": null,
229
+ "head_dim": 128,
230
+ "hidden_act": "silu",
231
+ "hidden_size": 1024,
232
+ "id2label": {
233
+ "0": "LABEL_0",
234
+ "1": "LABEL_1"
235
+ },
236
+ "initializer_range": 0.02,
237
+ "intermediate_size": 2048,
238
+ "is_decoder": false,
239
+ "is_encoder_decoder": false,
240
+ "label2id": {
241
+ "LABEL_0": 0,
242
+ "LABEL_1": 1
243
+ },
244
+ "length_penalty": 1.0,
245
+ "max_length": 20,
246
+ "max_position_embeddings": 65536,
247
+ "min_length": 0,
248
+ "mlp_only_layers": [],
249
+ "model_type": "qwen3_omni_moe_talker_text",
250
+ "moe_intermediate_size": 384,
251
+ "no_repeat_ngram_size": 0,
252
+ "norm_topk_prob": true,
253
+ "num_attention_heads": 16,
254
+ "num_beam_groups": 1,
255
+ "num_beams": 1,
256
+ "num_experts": 128,
257
+ "num_experts_per_tok": 6,
258
+ "num_hidden_layers": 20,
259
+ "num_key_value_heads": 2,
260
+ "num_return_sequences": 1,
261
+ "output_attentions": false,
262
+ "output_hidden_states": false,
263
+ "output_router_logits": false,
264
+ "output_scores": false,
265
+ "pad_token_id": null,
266
+ "prefix": null,
267
+ "problem_type": null,
268
+ "pruned_heads": {},
269
+ "remove_invalid_values": false,
270
+ "repetition_penalty": 1.0,
271
+ "return_dict": true,
272
+ "return_dict_in_generate": false,
273
+ "rms_norm_eps": 1e-06,
274
+ "rope_scaling": {
275
+ "interleaved": true,
276
+ "mrope_section": [
277
+ 24,
278
+ 20,
279
+ 20
280
+ ],
281
+ "rope_type": "default",
282
+ "type": "default"
283
+ },
284
+ "rope_theta": 1000000,
285
+ "router_aux_loss_coef": 0.001,
286
+ "sep_token_id": null,
287
+ "shared_expert_intermediate_size": 768,
288
+ "sliding_window": null,
289
+ "suppress_tokens": null,
290
+ "task_specific_params": null,
291
+ "temperature": 1.0,
292
+ "tie_encoder_decoder": false,
293
+ "tie_word_embeddings": false,
294
+ "tokenizer_class": null,
295
+ "top_k": 50,
296
+ "top_p": 1.0,
297
+ "torchscript": false,
298
+ "typical_p": 1.0,
299
+ "use_cache": true,
300
+ "use_sliding_window": false,
301
+ "vocab_size": 3072
302
+ },
303
+ "thinker_hidden_size": 2048,
304
+ "video_token_id": 151656,
305
+ "vision_start_token_id": 151652
306
+ },
307
+ "thinker_config": {
308
+ "audio_config": {
309
+ "_name_or_path": "",
310
+ "activation_dropout": 0,
311
+ "activation_function": "gelu",
312
+ "add_cross_attention": false,
313
+ "architectures": null,
314
+ "attention_dropout": 0,
315
+ "bad_words_ids": null,
316
+ "begin_suppress_tokens": null,
317
+ "bos_token_id": null,
318
+ "chunk_size_feed_forward": 0,
319
+ "conv_chunksize": 500,
320
+ "cross_attention_hidden_size": null,
321
+ "d_model": 1280,
322
+ "decoder_start_token_id": null,
323
+ "diversity_penalty": 0.0,
324
+ "do_sample": false,
325
+ "downsample_hidden_size": 480,
326
+ "dropout": 0,
327
+ "dtype": null,
328
+ "early_stopping": false,
329
+ "encoder_attention_heads": 20,
330
+ "encoder_ffn_dim": 5120,
331
+ "encoder_layers": 32,
332
+ "encoder_no_repeat_ngram_size": 0,
333
+ "eos_token_id": null,
334
+ "exponential_decay_length_penalty": null,
335
+ "finetuning_task": null,
336
+ "forced_bos_token_id": null,
337
+ "forced_eos_token_id": null,
338
+ "id2label": {
339
+ "0": "LABEL_0",
340
+ "1": "LABEL_1"
341
+ },
342
+ "initializer_range": 0.02,
343
+ "is_decoder": false,
344
+ "is_encoder_decoder": false,
345
+ "label2id": {
346
+ "LABEL_0": 0,
347
+ "LABEL_1": 1
348
+ },
349
+ "length_penalty": 1.0,
350
+ "max_length": 20,
351
+ "max_source_positions": 1500,
352
+ "min_length": 0,
353
+ "model_type": "qwen3_omni_moe_audio_encoder",
354
+ "n_window": 50,
355
+ "n_window_infer": 800,
356
+ "no_repeat_ngram_size": 0,
357
+ "num_beam_groups": 1,
358
+ "num_beams": 1,
359
+ "num_hidden_layers": 32,
360
+ "num_mel_bins": 128,
361
+ "num_return_sequences": 1,
362
+ "output_attentions": false,
363
+ "output_dim": 2048,
364
+ "output_hidden_states": false,
365
+ "output_scores": false,
366
+ "pad_token_id": null,
367
+ "prefix": null,
368
+ "problem_type": null,
369
+ "pruned_heads": {},
370
+ "remove_invalid_values": false,
371
+ "repetition_penalty": 1.0,
372
+ "return_dict": true,
373
+ "return_dict_in_generate": false,
374
+ "scale_embedding": false,
375
+ "sep_token_id": null,
376
+ "suppress_tokens": null,
377
+ "task_specific_params": null,
378
+ "temperature": 1.0,
379
+ "tf_legacy_loss": false,
380
+ "tie_encoder_decoder": false,
381
+ "tie_word_embeddings": true,
382
+ "tokenizer_class": null,
383
+ "top_k": 50,
384
+ "top_p": 1.0,
385
+ "torchscript": false,
386
+ "typical_p": 1.0,
387
+ "use_bfloat16": false
388
+ },
389
+ "audio_end_token_id": 151670,
390
+ "audio_start_token_id": 151669,
391
+ "audio_token_id": 151675,
392
+ "dtype": "bfloat16",
393
+ "image_token_id": 151655,
394
+ "initializer_range": 0.02,
395
+ "model_type": "qwen3_omni_moe_thinker",
396
+ "position_id_per_seconds": 13,
397
+ "seconds_per_chunk": 2,
398
+ "text_config": {
399
+ "_name_or_path": "",
400
+ "add_cross_attention": false,
401
+ "architectures": null,
402
+ "attention_bias": false,
403
+ "attention_dropout": 0.0,
404
+ "bad_words_ids": null,
405
+ "begin_suppress_tokens": null,
406
+ "bos_token_id": null,
407
+ "chunk_size_feed_forward": 0,
408
+ "cross_attention_hidden_size": null,
409
+ "decoder_sparse_step": 1,
410
+ "decoder_start_token_id": null,
411
+ "diversity_penalty": 0.0,
412
+ "do_sample": false,
413
+ "dtype": null,
414
+ "early_stopping": false,
415
+ "encoder_no_repeat_ngram_size": 0,
416
+ "eos_token_id": null,
417
+ "exponential_decay_length_penalty": null,
418
+ "finetuning_task": null,
419
+ "forced_bos_token_id": null,
420
+ "forced_eos_token_id": null,
421
+ "head_dim": 128,
422
+ "hidden_act": "silu",
423
+ "hidden_size": 2048,
424
+ "id2label": {
425
+ "0": "LABEL_0",
426
+ "1": "LABEL_1"
427
+ },
428
+ "initializer_range": 0.02,
429
+ "intermediate_size": 768,
430
+ "is_decoder": false,
431
+ "is_encoder_decoder": false,
432
+ "label2id": {
433
+ "LABEL_0": 0,
434
+ "LABEL_1": 1
435
+ },
436
+ "length_penalty": 1.0,
437
+ "max_length": 20,
438
+ "max_position_embeddings": 65536,
439
+ "min_length": 0,
440
+ "mlp_only_layers": [],
441
+ "model_type": "qwen3_omni_moe_text",
442
+ "moe_intermediate_size": 768,
443
+ "no_repeat_ngram_size": 0,
444
+ "norm_topk_prob": true,
445
+ "num_attention_heads": 32,
446
+ "num_beam_groups": 1,
447
+ "num_beams": 1,
448
+ "num_experts": 128,
449
+ "num_experts_per_tok": 8,
450
+ "num_hidden_layers": 48,
451
+ "num_key_value_heads": 4,
452
+ "num_return_sequences": 1,
453
+ "output_attentions": false,
454
+ "output_hidden_states": false,
455
+ "output_router_logits": false,
456
+ "output_scores": false,
457
+ "pad_token_id": null,
458
+ "prefix": null,
459
+ "problem_type": null,
460
+ "pruned_heads": {},
461
+ "remove_invalid_values": false,
462
+ "repetition_penalty": 1.0,
463
+ "return_dict": true,
464
+ "return_dict_in_generate": false,
465
+ "rms_norm_eps": 1e-06,
466
+ "rope_scaling": {
467
+ "interleaved": true,
468
+ "mrope_interleaved": true,
469
+ "mrope_section": [
470
+ 24,
471
+ 20,
472
+ 20
473
+ ],
474
+ "rope_type": "default",
475
+ "type": "default"
476
+ },
477
+ "rope_theta": 1000000,
478
+ "router_aux_loss_coef": 0.001,
479
+ "sep_token_id": null,
480
+ "shared_expert_intermediate_size": 0,
481
+ "sliding_window": null,
482
+ "suppress_tokens": null,
483
+ "task_specific_params": null,
484
+ "temperature": 1.0,
485
+ "tf_legacy_loss": false,
486
+ "tie_encoder_decoder": false,
487
+ "tie_word_embeddings": false,
488
+ "tokenizer_class": null,
489
+ "top_k": 50,
490
+ "top_p": 1.0,
491
+ "torchscript": false,
492
+ "typical_p": 1.0,
493
+ "use_bfloat16": false,
494
+ "use_cache": true,
495
+ "use_qk_norm": true,
496
+ "use_sliding_window": false,
497
+ "vocab_size": 152064
498
+ },
499
+ "user_token_id": 872,
500
+ "video_token_id": 151656,
501
+ "vision_config": {
502
+ "_name_or_path": "",
503
+ "add_cross_attention": false,
504
+ "apply_vit_abs_pos_embed": true,
505
+ "architectures": null,
506
+ "bad_words_ids": null,
507
+ "begin_suppress_tokens": null,
508
+ "bos_token_id": null,
509
+ "chunk_size_feed_forward": 0,
510
+ "cross_attention_hidden_size": null,
511
+ "decoder_start_token_id": null,
512
+ "deepstack_visual_indexes": [
513
+ 8,
514
+ 16,
515
+ 24
516
+ ],
517
+ "depth": 27,
518
+ "diversity_penalty": 0.0,
519
+ "do_sample": false,
520
+ "dtype": null,
521
+ "early_stopping": false,
522
+ "encoder_no_repeat_ngram_size": 0,
523
+ "eos_token_id": null,
524
+ "exponential_decay_length_penalty": null,
525
+ "finetuning_task": null,
526
+ "forced_bos_token_id": null,
527
+ "forced_eos_token_id": null,
528
+ "hidden_act": "gelu_pytorch_tanh",
529
+ "hidden_size": 1152,
530
+ "id2label": {
531
+ "0": "LABEL_0",
532
+ "1": "LABEL_1"
533
+ },
534
+ "image_size": 768,
535
+ "in_channels": 3,
536
+ "in_chans": 3,
537
+ "initializer_range": 0.02,
538
+ "intermediate_size": 4304,
539
+ "is_decoder": false,
540
+ "is_encoder_decoder": false,
541
+ "label2id": {
542
+ "LABEL_0": 0,
543
+ "LABEL_1": 1
544
+ },
545
+ "length_penalty": 1.0,
546
+ "max_length": 20,
547
+ "min_length": 0,
548
+ "model_type": "qwen3_omni_moe_vision_encoder",
549
+ "no_repeat_ngram_size": 0,
550
+ "num_beam_groups": 1,
551
+ "num_beams": 1,
552
+ "num_heads": 16,
553
+ "num_position_embeddings": 2304,
554
+ "num_return_sequences": 1,
555
+ "out_hidden_size": 2048,
556
+ "output_attentions": false,
557
+ "output_hidden_states": false,
558
+ "output_scores": false,
559
+ "pad_token_id": null,
560
+ "patch_size": 16,
561
+ "prefix": null,
562
+ "problem_type": null,
563
+ "pruned_heads": {},
564
+ "remove_invalid_values": false,
565
+ "repetition_penalty": 1.0,
566
+ "return_dict": true,
567
+ "return_dict_in_generate": false,
568
+ "sep_token_id": null,
569
+ "spatial_merge_size": 2,
570
+ "spatial_patch_size": 16,
571
+ "suppress_tokens": null,
572
+ "task_specific_params": null,
573
+ "temperature": 1.0,
574
+ "temporal_patch_size": 2,
575
+ "tf_legacy_loss": false,
576
+ "tie_encoder_decoder": false,
577
+ "tie_word_embeddings": true,
578
+ "tokenizer_class": null,
579
+ "tokens_per_second": 2,
580
+ "top_k": 50,
581
+ "top_p": 1.0,
582
+ "torchscript": false,
583
+ "typical_p": 1.0,
584
+ "use_bfloat16": false
585
+ },
586
+ "vision_end_token_id": 151653,
587
+ "vision_start_token_id": 151652
588
+ },
589
+ "tie_word_embeddings": false,
590
+ "transformers_version": "4.57.0.dev0",
591
+ "tts_bos_token_id": 151672,
592
+ "tts_eos_token_id": 151673,
593
+ "tts_pad_token_id": 151671,
594
+ "user_token_id": 872
595
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "enable_audio_output": false,
3
+ "talker_max_new_tokens": 4096,
4
+ "talker_repetition_penalty": 1.05,
5
+ "talker_temperature": 0.9,
6
+ "talker_top_k": 50,
7
+ "talker_top_p": 1.0,
8
+ "transformers_version": "4.57.0.dev0"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:523b93b316f0ae857dabe38d844cefbcddf6694d91d4581c92970d57e8e15ecb
3
+ size 32104574432
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
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
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": 480000,
23
+ "nb_max_frames": 3000,
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
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*mlp.gate$', 're:.*shared_expert_gate$', 're:.*router$']
6
+ scheme: FP8_DYNAMIC
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 sha256:3f8b4ea46bb078feef22cc9c2d29cbfe4c6440d3f0fb163db4bf6998a6cb4207
3
+ size 11424265
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 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "dither": 0.0,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "feature_extractor_type": "WhisperFeatureExtractor",
14
+ "feature_size": 128,
15
+ "fps": null,
16
+ "hop_length": 160,
17
+ "image_mean": [
18
+ 0.5,
19
+ 0.5,
20
+ 0.5
21
+ ],
22
+ "image_std": [
23
+ 0.5,
24
+ 0.5,
25
+ 0.5
26
+ ],
27
+ "input_data_format": null,
28
+ "max_frames": 768,
29
+ "max_pixels": 12845056,
30
+ "merge_size": 2,
31
+ "min_frames": 4,
32
+ "min_pixels": 3136,
33
+ "n_fft": 400,
34
+ "n_samples": 4800000,
35
+ "nb_max_frames": 30000,
36
+ "num_frames": null,
37
+ "pad_size": null,
38
+ "padding_side": "right",
39
+ "padding_value": 0.0,
40
+ "patch_size": 16,
41
+ "processor_class": "Qwen3OmniMoeProcessor",
42
+ "resample": 3,
43
+ "rescale_factor": 0.00392156862745098,
44
+ "return_attention_mask": true,
45
+ "return_metadata": false,
46
+ "sampling_rate": 16000,
47
+ "size": {
48
+ "longest_edge": 12845056,
49
+ "shortest_edge": 3136
50
+ },
51
+ "temporal_patch_size": 2,
52
+ "video_metadata": null,
53
+ "video_processor_type": "Qwen2VLVideoProcessor"
54
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff