littlebird13 commited on
Commit
0e20e2b
·
verified ·
1 Parent(s): 302ffa9

Upload folder using huggingface_hub

Browse files
chat_template.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {{- \"<|vision_start|><|image_pad|><|vision_end|>\" }}\n {%- elif content.type == 'audio' or 'audio' in content or 'audio_url' in content %}\n {{- \"<|audio_start|><|audio_pad|><|audio_end|>\" }}\n {%- elif content.type == 'video' or 'video' in content %}\n {{- \"<|vision_start|><|video_pad|><|vision_end|>\" }}\n {%- elif content.type == 'text' %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- endif %}\n {{- '\\n\\n' }}\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 %}"}
config.json ADDED
@@ -0,0 +1,484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
41
+ "im_end_token_id": 151645,
42
+ "im_start_token_id": 151644,
43
+ "model_type": "qwen3_omni_moe",
44
+ "system_token_id": 8948,
45
+ "talker_config": {
46
+ "text_config":{
47
+ "attention_bias": false,
48
+ "attention_dropout": 0,
49
+ "decoder_sparse_step": 1,
50
+ "head_dim": 128,
51
+ "hidden_act": "silu",
52
+ "hidden_size": 1024,
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 2048,
55
+ "max_position_embeddings": 65536,
56
+ "mlp_only_layers": [],
57
+ "moe_intermediate_size": 384,
58
+ "norm_topk_prob": true,
59
+ "num_attention_heads": 16,
60
+ "num_experts": 128,
61
+ "num_experts_per_tok": 6,
62
+ "num_hidden_layers": 20,
63
+ "num_key_value_heads": 2,
64
+ "rms_norm_eps": 1e-06,
65
+ "rope_scaling": {
66
+ "interleaved": true,
67
+ "mrope_section": [
68
+ 24,
69
+ 20,
70
+ 20
71
+ ],
72
+ "rope_type": "default",
73
+ "type": "default"
74
+ },
75
+ "rope_theta": 1000000,
76
+ "router_aux_loss_coef": 0.001,
77
+ "shared_expert_intermediate_size": 768,
78
+ "sliding_window": null,
79
+ "use_cache": true,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 3072
82
+ },
83
+ "accept_hidden_layer": 24,
84
+ "audio_end_token_id": 151670,
85
+ "audio_start_token_id": 151669,
86
+ "audio_token_id": 151675,
87
+ "code_predictor_config": {
88
+ "_name_or_path": "",
89
+ "add_cross_attention": false,
90
+ "architectures": null,
91
+ "attention_bias": false,
92
+ "attention_dropout": 0,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "dtype": null,
102
+ "early_stopping": false,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "eos_token_id": null,
105
+ "exponential_decay_length_penalty": null,
106
+ "finetuning_task": null,
107
+ "forced_bos_token_id": null,
108
+ "forced_eos_token_id": null,
109
+ "head_dim": 128,
110
+ "hidden_act": "silu",
111
+ "hidden_size": 1024,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "initializer_range": 0.02,
117
+ "intermediate_size": 3072,
118
+ "is_decoder": false,
119
+ "is_encoder_decoder": false,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "layer_types": [
125
+ "full_attention",
126
+ "full_attention",
127
+ "full_attention",
128
+ "full_attention",
129
+ "full_attention"
130
+ ],
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "max_position_embeddings": 32768,
134
+ "max_window_layers": 28,
135
+ "min_length": 0,
136
+ "model_type": "qwen3_omni_moe_talker_code_predictor",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_code_groups": 16,
142
+ "num_hidden_layers": 5,
143
+ "num_key_value_heads": 8,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": null,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "rms_norm_eps": 1e-06,
157
+ "rope_scaling": null,
158
+ "rope_theta": 1000000,
159
+ "sep_token_id": null,
160
+ "sliding_window": null,
161
+ "suppress_tokens": null,
162
+ "task_specific_params": null,
163
+ "temperature": 1.0,
164
+ "tf_legacy_loss": false,
165
+ "tie_encoder_decoder": false,
166
+ "tie_word_embeddings": false,
167
+ "tokenizer_class": null,
168
+ "top_k": 50,
169
+ "top_p": 1.0,
170
+ "torchscript": false,
171
+ "typical_p": 1.0,
172
+ "use_bfloat16": false,
173
+ "use_cache": true,
174
+ "use_sliding_window": false,
175
+ "vocab_size": 2048
176
+ },
177
+ "codec_bos_id": 2149,
178
+ "codec_eos_token_id": 2150,
179
+ "codec_nothink_id": 2155,
180
+ "codec_pad_id": 2148,
181
+ "codec_think_bos_id": 2156,
182
+ "codec_think_eos_id": 2157,
183
+ "image_token_id": 151655,
184
+ "model_type": "qwen3_omni_moe_talker",
185
+ "num_code_groups": 16,
186
+ "output_router_logits": false,
187
+ "position_id_per_seconds": 13,
188
+ "seconds_per_chunk": 2,
189
+ "spatial_merge_size": 2,
190
+ "speaker_id": {
191
+ "chelsie": 2301,
192
+ "ethan": 2302,
193
+ "aiden": 2303
194
+ },
195
+ "thinker_hidden_size": 2048,
196
+ "video_token_id": 151656,
197
+ "vision_start_token_id": 151652
198
+ },
199
+ "thinker_config": {
200
+ "audio_config": {
201
+ "_name_or_path": "",
202
+ "activation_dropout": 0,
203
+ "activation_function": "gelu",
204
+ "add_cross_attention": false,
205
+ "architectures": null,
206
+ "attention_dropout": 0,
207
+ "bad_words_ids": null,
208
+ "begin_suppress_tokens": null,
209
+ "bos_token_id": null,
210
+ "chunk_size_feed_forward": 0,
211
+ "conv_chunksize": 500,
212
+ "cross_attention_hidden_size": null,
213
+ "d_model": 1280,
214
+ "decoder_start_token_id": null,
215
+ "diversity_penalty": 0.0,
216
+ "do_sample": false,
217
+ "downsample_hidden_size":480,
218
+ "dropout": 0,
219
+ "dtype": null,
220
+ "early_stopping": false,
221
+ "encoder_attention_heads": 20,
222
+ "encoder_ffn_dim": 5120,
223
+ "encoder_layers": 32,
224
+ "encoder_no_repeat_ngram_size": 0,
225
+ "eos_token_id": null,
226
+ "exponential_decay_length_penalty": null,
227
+ "finetuning_task": null,
228
+ "forced_bos_token_id": null,
229
+ "forced_eos_token_id": null,
230
+ "id2label": {
231
+ "0": "LABEL_0",
232
+ "1": "LABEL_1"
233
+ },
234
+ "initializer_range": 0.02,
235
+ "is_decoder": false,
236
+ "is_encoder_decoder": false,
237
+ "label2id": {
238
+ "LABEL_0": 0,
239
+ "LABEL_1": 1
240
+ },
241
+ "length_penalty": 1.0,
242
+ "max_length": 20,
243
+ "max_source_positions": 1500,
244
+ "min_length": 0,
245
+ "model_type": "qwen3_omni_moe_audio_encoder",
246
+ "n_window": 50,
247
+ "n_window_infer": 800,
248
+ "no_repeat_ngram_size": 0,
249
+ "num_beam_groups": 1,
250
+ "num_beams": 1,
251
+ "num_hidden_layers": 32,
252
+ "num_mel_bins": 128,
253
+ "num_return_sequences": 1,
254
+ "output_attentions": false,
255
+ "output_dim": 2048,
256
+ "output_hidden_states": false,
257
+ "output_scores": false,
258
+ "pad_token_id": null,
259
+ "prefix": null,
260
+ "problem_type": null,
261
+ "pruned_heads": {},
262
+ "remove_invalid_values": false,
263
+ "repetition_penalty": 1.0,
264
+ "return_dict": true,
265
+ "return_dict_in_generate": false,
266
+ "scale_embedding": false,
267
+ "sep_token_id": null,
268
+ "suppress_tokens": null,
269
+ "task_specific_params": null,
270
+ "temperature": 1.0,
271
+ "tf_legacy_loss": false,
272
+ "tie_encoder_decoder": false,
273
+ "tie_word_embeddings": true,
274
+ "tokenizer_class": null,
275
+ "top_k": 50,
276
+ "top_p": 1.0,
277
+ "torchscript": false,
278
+ "typical_p": 1.0,
279
+ "use_bfloat16": false
280
+ },
281
+ "audio_end_token_id": 151670,
282
+ "audio_start_token_id": 151669,
283
+ "audio_token_id": 151675,
284
+ "dtype": "bfloat16",
285
+ "image_token_id": 151655,
286
+ "initializer_range": 0.02,
287
+ "model_type": "qwen3_omni_moe_thinker",
288
+ "position_id_per_seconds": 13,
289
+ "seconds_per_chunk": 2,
290
+ "text_config": {
291
+ "_name_or_path": "",
292
+ "add_cross_attention": false,
293
+ "architectures": null,
294
+ "attention_bias": false,
295
+ "attention_dropout": 0.0,
296
+ "bad_words_ids": null,
297
+ "begin_suppress_tokens": null,
298
+ "bos_token_id": null,
299
+ "chunk_size_feed_forward": 0,
300
+ "cross_attention_hidden_size": null,
301
+ "decoder_sparse_step": 1,
302
+ "decoder_start_token_id": null,
303
+ "diversity_penalty": 0.0,
304
+ "do_sample": false,
305
+ "dtype": null,
306
+ "early_stopping": false,
307
+ "encoder_no_repeat_ngram_size": 0,
308
+ "eos_token_id": null,
309
+ "exponential_decay_length_penalty": null,
310
+ "finetuning_task": null,
311
+ "forced_bos_token_id": null,
312
+ "forced_eos_token_id": null,
313
+ "head_dim": 128,
314
+ "hidden_act": "silu",
315
+ "hidden_size": 2048,
316
+ "id2label": {
317
+ "0": "LABEL_0",
318
+ "1": "LABEL_1"
319
+ },
320
+ "initializer_range": 0.02,
321
+ "intermediate_size": 768,
322
+ "is_decoder": false,
323
+ "is_encoder_decoder": false,
324
+ "label2id": {
325
+ "LABEL_0": 0,
326
+ "LABEL_1": 1
327
+ },
328
+ "length_penalty": 1.0,
329
+ "max_length": 20,
330
+ "max_position_embeddings": 65536,
331
+ "min_length": 0,
332
+ "mlp_only_layers": [],
333
+ "model_type": "qwen3_omni_moe_text",
334
+ "moe_intermediate_size": 768,
335
+ "no_repeat_ngram_size": 0,
336
+ "norm_topk_prob": true,
337
+ "num_attention_heads": 32,
338
+ "num_beam_groups": 1,
339
+ "num_beams": 1,
340
+ "num_experts": 128,
341
+ "num_experts_per_tok": 8,
342
+ "num_hidden_layers": 48,
343
+ "num_key_value_heads": 4,
344
+ "num_return_sequences": 1,
345
+ "output_attentions": false,
346
+ "output_hidden_states": false,
347
+ "output_router_logits": false,
348
+ "output_scores": false,
349
+ "pad_token_id": null,
350
+ "prefix": null,
351
+ "problem_type": null,
352
+ "pruned_heads": {},
353
+ "remove_invalid_values": false,
354
+ "repetition_penalty": 1.0,
355
+ "return_dict": true,
356
+ "return_dict_in_generate": false,
357
+ "rms_norm_eps": 1e-06,
358
+ "rope_scaling": {
359
+ "interleaved": true,
360
+ "mrope_section": [
361
+ 24,
362
+ 20,
363
+ 20
364
+ ],
365
+ "rope_type": "default",
366
+ "type": "default"
367
+ },
368
+ "rope_theta": 1000000,
369
+ "router_aux_loss_coef": 0.001,
370
+ "sep_token_id": null,
371
+ "shared_expert_intermediate_size": 0,
372
+ "sliding_window": null,
373
+ "suppress_tokens": null,
374
+ "task_specific_params": null,
375
+ "temperature": 1.0,
376
+ "tf_legacy_loss": false,
377
+ "tie_encoder_decoder": false,
378
+ "tie_word_embeddings": false,
379
+ "tokenizer_class": null,
380
+ "top_k": 50,
381
+ "top_p": 1.0,
382
+ "torchscript": false,
383
+ "typical_p": 1.0,
384
+ "use_bfloat16": false,
385
+ "use_cache": true,
386
+ "use_qk_norm": true,
387
+ "use_sliding_window": false,
388
+ "vocab_size": 152064
389
+ },
390
+ "user_token_id": 872,
391
+ "video_token_id": 151656,
392
+ "vision_config": {
393
+ "_name_or_path": "",
394
+ "add_cross_attention": false,
395
+ "apply_vit_abs_pos_embed": true,
396
+ "architectures": null,
397
+ "bad_words_ids": null,
398
+ "begin_suppress_tokens": null,
399
+ "bos_token_id": null,
400
+ "chunk_size_feed_forward": 0,
401
+ "cross_attention_hidden_size": null,
402
+ "decoder_start_token_id": null,
403
+ "deepstack_visual_indexes": [
404
+ 8,
405
+ 16,
406
+ 24
407
+ ],
408
+ "depth": 27,
409
+ "diversity_penalty": 0.0,
410
+ "do_sample": false,
411
+ "dtype": null,
412
+ "early_stopping": false,
413
+ "encoder_no_repeat_ngram_size": 0,
414
+ "eos_token_id": null,
415
+ "exponential_decay_length_penalty": null,
416
+ "finetuning_task": null,
417
+ "forced_bos_token_id": null,
418
+ "forced_eos_token_id": null,
419
+ "hidden_act": "gelu_pytorch_tanh",
420
+ "hidden_size": 1152,
421
+ "id2label": {
422
+ "0": "LABEL_0",
423
+ "1": "LABEL_1"
424
+ },
425
+ "image_size": 768,
426
+ "in_channels": 3,
427
+ "in_chans": 3,
428
+ "initializer_range": 0.02,
429
+ "intermediate_size": 4304,
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
+ "min_length": 0,
439
+ "model_type": "qwen3_omni_moe_vision_encoder",
440
+ "no_repeat_ngram_size": 0,
441
+ "num_beam_groups": 1,
442
+ "num_beams": 1,
443
+ "num_heads": 16,
444
+ "num_return_sequences": 1,
445
+ "out_hidden_size": 2048,
446
+ "output_attentions": false,
447
+ "output_hidden_states": false,
448
+ "output_scores": false,
449
+ "pad_token_id": null,
450
+ "patch_size": 16,
451
+ "prefix": null,
452
+ "problem_type": null,
453
+ "pruned_heads": {},
454
+ "remove_invalid_values": false,
455
+ "repetition_penalty": 1.0,
456
+ "return_dict": true,
457
+ "return_dict_in_generate": false,
458
+ "sep_token_id": null,
459
+ "spatial_merge_size": 2,
460
+ "spatial_patch_size": 16,
461
+ "suppress_tokens": null,
462
+ "task_specific_params": null,
463
+ "temperature": 1.0,
464
+ "temporal_patch_size": 2,
465
+ "tf_legacy_loss": false,
466
+ "tie_encoder_decoder": false,
467
+ "tie_word_embeddings": true,
468
+ "tokenizer_class": null,
469
+ "tokens_per_second": 2,
470
+ "top_k": 50,
471
+ "top_p": 1.0,
472
+ "torchscript": false,
473
+ "typical_p": 1.0,
474
+ "use_bfloat16": false
475
+ },
476
+ "vision_end_token_id": 151653,
477
+ "vision_start_token_id": 151652
478
+ },
479
+ "transformers_version": "4.57.0.dev0",
480
+ "tts_bos_token_id": 151672,
481
+ "tts_eos_token_id": 151673,
482
+ "tts_pad_token_id": 151671,
483
+ "user_token_id": 872
484
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "talker_max_new_tokens": 4096,
3
+ "talker_repetition_penalty": 1.05,
4
+ "talker_temperature": 0.9,
5
+ "talker_top_k": 50,
6
+ "talker_top_p": 1.0
7
+ }
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:f95d142b727fbd0698f0ed9478e222d4f29467df855e21862e46bd1401049065
3
+ size 4997899632
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320c1f31f7ddc4efd2501891590eca2c481ce4eca3db33d70ebbb637dae85764
3
+ size 4997754216
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306f06b05ef032f1fa51eb62e72c3432324e7a084fa0d15ed17ff856adffcf33
3
+ size 4997754216
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb551f433bfb4d83a5843e433e74688d71a96eeb1b62217b37d719026d559b5
3
+ size 4997755648
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aec5e8cc0e0b179a81f690af31a1149238f4b1d18ac60e3f690020fdf7d915f
3
+ size 4997755792
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff40a3d9e9c59a35a10257c1c5b216f472e6a102a4d6059bd31183eee03cb4c
3
+ size 4997755792
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d84cc1d47178850f9ba1fe9c01f45ee63d9a8b9975f92821ee2b4a0387860b
3
+ size 4997755792
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f369ccdc9d2d2a55df794005b23cdbce44494a72e4a0069a150ae471cfea720
3
+ size 4997755792
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980f754b21c4b20f36e02d184b792f5625f7c9d24b8a5c9da94287cf3cfde11b
3
+ size 4997755792
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5a798376321d74df2eb3f235e1c8c68669f09b0c753b5698a16e681204d808
3
+ size 4997755792
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7c051bd391c89279b43e7342ff4a243ad2ba2144f4aa62233fd2b02d72fce0
3
+ size 4997755792
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b09a9367cd31ebf928e87b9eaf002492379d9d21d352b480854c2fbe6d9978
3
+ size 4997755792
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b7441c3a33e066d109cd6338e74ed680de9aa407d4df66eba5cb3c15c6d738
3
+ size 4999771808
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f09f187ff7b469a8937b39b8ac772e539e0d61311526c345558c5e6a6eb09a
3
+ size 4996618552
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68880d566a50643807a4e73f5227c4f468bb31532925ed5fae78a51bdd39492a
3
+ size 553698794
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