Hugging Face's logo

oulinyu
/
qwen3-omni-sft-grpo-merge

Safetensors
English
qwen3_omni_moe
agent
Omni
Model card Files
xet
 Community
oulinyu commited on
Commit
6ae7dd4
·
verified ·
1 Parent(s): bf821f7

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 +548 -0
  5. generation_config.json +8 -0
  6. merges.txt +0 -0
  7. model-00001-of-00015.safetensors +3 -0
  8. model-00002-of-00015.safetensors +3 -0
  9. model-00003-of-00015.safetensors +3 -0
  10. model-00004-of-00015.safetensors +3 -0
  11. model-00005-of-00015.safetensors +3 -0
  12. model-00006-of-00015.safetensors +3 -0
  13. model-00007-of-00015.safetensors +3 -0
  14. model-00008-of-00015.safetensors +3 -0
  15. model-00009-of-00015.safetensors +3 -0
  16. model-00010-of-00015.safetensors +3 -0
  17. model-00011-of-00015.safetensors +3 -0
  18. model-00012-of-00015.safetensors +3 -0
  19. model-00013-of-00015.safetensors +3 -0
  20. model-00014-of-00015.safetensors +3 -0
  21. model-00015-of-00015.safetensors +3 -0
  22. model.safetensors.index.json +0 -0
  23. preprocessor_config.json +30 -0
  24. special_tokens_map.json +44 -0
  25. tokenizer.json +3 -0
  26. tokenizer_config.json +316 -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 +1,548 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "accept_hidden_layer": 24,
47
+ "audio_end_token_id": 151670,
48
+ "audio_start_token_id": 151669,
49
+ "audio_token_id": 151675,
50
+ "code_predictor_config": {
51
+ "_name_or_path": "",
52
+ "add_cross_attention": false,
53
+ "architectures": null,
54
+ "attention_bias": false,
55
+ "attention_dropout": 0,
56
+ "bad_words_ids": null,
57
+ "begin_suppress_tokens": null,
58
+ "bos_token_id": null,
59
+ "chunk_size_feed_forward": 0,
60
+ "cross_attention_hidden_size": null,
61
+ "decoder_start_token_id": null,
62
+ "diversity_penalty": 0.0,
63
+ "do_sample": false,
64
+ "dtype": null,
65
+ "early_stopping": false,
66
+ "encoder_no_repeat_ngram_size": 0,
67
+ "eos_token_id": null,
68
+ "exponential_decay_length_penalty": null,
69
+ "finetuning_task": null,
70
+ "forced_bos_token_id": null,
71
+ "forced_eos_token_id": null,
72
+ "head_dim": 128,
73
+ "hidden_act": "silu",
74
+ "hidden_size": 1024,
75
+ "id2label": {
76
+ "0": "LABEL_0",
77
+ "1": "LABEL_1"
78
+ },
79
+ "initializer_range": 0.02,
80
+ "intermediate_size": 3072,
81
+ "is_decoder": false,
82
+ "is_encoder_decoder": false,
83
+ "label2id": {
84
+ "LABEL_0": 0,
85
+ "LABEL_1": 1
86
+ },
87
+ "layer_types": [
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention"
93
+ ],
94
+ "length_penalty": 1.0,
95
+ "max_length": 20,
96
+ "max_position_embeddings": 32768,
97
+ "max_window_layers": 28,
98
+ "min_length": 0,
99
+ "model_type": "qwen3_omni_moe_talker_code_predictor",
100
+ "no_repeat_ngram_size": 0,
101
+ "num_attention_heads": 16,
102
+ "num_beam_groups": 1,
103
+ "num_beams": 1,
104
+ "num_code_groups": 16,
105
+ "num_hidden_layers": 5,
106
+ "num_key_value_heads": 8,
107
+ "num_return_sequences": 1,
108
+ "output_attentions": false,
109
+ "output_hidden_states": false,
110
+ "output_scores": false,
111
+ "pad_token_id": null,
112
+ "prefix": null,
113
+ "problem_type": null,
114
+ "pruned_heads": {},
115
+ "remove_invalid_values": false,
116
+ "repetition_penalty": 1.0,
117
+ "return_dict": true,
118
+ "return_dict_in_generate": false,
119
+ "rms_norm_eps": 1e-06,
120
+ "rope_scaling": null,
121
+ "rope_theta": 1000000,
122
+ "sep_token_id": null,
123
+ "sliding_window": null,
124
+ "suppress_tokens": null,
125
+ "task_specific_params": null,
126
+ "temperature": 1.0,
127
+ "tf_legacy_loss": false,
128
+ "tie_encoder_decoder": false,
129
+ "tie_word_embeddings": false,
130
+ "tokenizer_class": null,
131
+ "top_k": 50,
132
+ "top_p": 1.0,
133
+ "torchscript": false,
134
+ "typical_p": 1.0,
135
+ "use_bfloat16": false,
136
+ "use_cache": true,
137
+ "use_sliding_window": false,
138
+ "vocab_size": 2048
139
+ },
140
+ "codec_bos_id": 2149,
141
+ "codec_eos_token_id": 2150,
142
+ "codec_nothink_id": 2155,
143
+ "codec_pad_id": 2148,
144
+ "codec_think_bos_id": 2156,
145
+ "codec_think_eos_id": 2157,
146
+ "image_token_id": 151655,
147
+ "model_type": "",
148
+ "num_code_groups": 16,
149
+ "output_router_logits": false,
150
+ "position_id_per_seconds": 13,
151
+ "seconds_per_chunk": 2,
152
+ "spatial_merge_size": 2,
153
+ "speaker_id": {
154
+ "aiden": 2303,
155
+ "chelsie": 2301,
156
+ "ethan": 2302
157
+ },
158
+ "text_config": {
159
+ "_name_or_path": "",
160
+ "add_cross_attention": false,
161
+ "architectures": null,
162
+ "attention_bias": false,
163
+ "attention_dropout": 0,
164
+ "bad_words_ids": null,
165
+ "begin_suppress_tokens": null,
166
+ "bos_token_id": null,
167
+ "chunk_size_feed_forward": 0,
168
+ "cross_attention_hidden_size": null,
169
+ "decoder_sparse_step": 1,
170
+ "decoder_start_token_id": null,
171
+ "diversity_penalty": 0.0,
172
+ "do_sample": false,
173
+ "dtype": null,
174
+ "early_stopping": false,
175
+ "encoder_no_repeat_ngram_size": 0,
176
+ "eos_token_id": null,
177
+ "exponential_decay_length_penalty": null,
178
+ "finetuning_task": null,
179
+ "forced_bos_token_id": null,
180
+ "forced_eos_token_id": null,
181
+ "head_dim": 128,
182
+ "hidden_act": "silu",
183
+ "hidden_size": 1024,
184
+ "id2label": {
185
+ "0": "LABEL_0",
186
+ "1": "LABEL_1"
187
+ },
188
+ "initializer_range": 0.02,
189
+ "intermediate_size": 2048,
190
+ "is_decoder": false,
191
+ "is_encoder_decoder": false,
192
+ "label2id": {
193
+ "LABEL_0": 0,
194
+ "LABEL_1": 1
195
+ },
196
+ "length_penalty": 1.0,
197
+ "max_length": 20,
198
+ "max_position_embeddings": 65536,
199
+ "min_length": 0,
200
+ "mlp_only_layers": [],
201
+ "model_type": "qwen3_omni_moe_talker_text",
202
+ "moe_intermediate_size": 384,
203
+ "no_repeat_ngram_size": 0,
204
+ "norm_topk_prob": true,
205
+ "num_attention_heads": 16,
206
+ "num_beam_groups": 1,
207
+ "num_beams": 1,
208
+ "num_experts": 128,
209
+ "num_experts_per_tok": 6,
210
+ "num_hidden_layers": 20,
211
+ "num_key_value_heads": 2,
212
+ "num_return_sequences": 1,
213
+ "output_attentions": false,
214
+ "output_hidden_states": false,
215
+ "output_router_logits": false,
216
+ "output_scores": false,
217
+ "pad_token_id": null,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "remove_invalid_values": false,
222
+ "repetition_penalty": 1.0,
223
+ "return_dict": true,
224
+ "return_dict_in_generate": false,
225
+ "rms_norm_eps": 1e-06,
226
+ "rope_scaling": {
227
+ "interleaved": true,
228
+ "mrope_section": [
229
+ 24,
230
+ 20,
231
+ 20
232
+ ],
233
+ "rope_type": "default",
234
+ "type": "default"
235
+ },
236
+ "rope_theta": 1000000,
237
+ "router_aux_loss_coef": 0.001,
238
+ "sep_token_id": null,
239
+ "shared_expert_intermediate_size": 768,
240
+ "sliding_window": null,
241
+ "suppress_tokens": null,
242
+ "task_specific_params": null,
243
+ "temperature": 1.0,
244
+ "tf_legacy_loss": false,
245
+ "tie_encoder_decoder": false,
246
+ "tie_word_embeddings": false,
247
+ "tokenizer_class": null,
248
+ "top_k": 50,
249
+ "top_p": 1.0,
250
+ "torchscript": false,
251
+ "typical_p": 1.0,
252
+ "use_bfloat16": false,
253
+ "use_cache": true,
254
+ "use_sliding_window": false,
255
+ "vocab_size": 3072
256
+ },
257
+ "thinker_hidden_size": 2048,
258
+ "video_token_id": 151656,
259
+ "vision_start_token_id": 151652
260
+ },
261
+ "thinker_config": {
262
+ "audio_config": {
263
+ "_name_or_path": "",
264
+ "activation_dropout": 0,
265
+ "activation_function": "gelu",
266
+ "add_cross_attention": false,
267
+ "architectures": null,
268
+ "attention_dropout": 0,
269
+ "bad_words_ids": null,
270
+ "begin_suppress_tokens": null,
271
+ "bos_token_id": null,
272
+ "chunk_size_feed_forward": 0,
273
+ "conv_chunksize": 500,
274
+ "cross_attention_hidden_size": null,
275
+ "d_model": 1280,
276
+ "decoder_start_token_id": null,
277
+ "diversity_penalty": 0.0,
278
+ "do_sample": false,
279
+ "downsample_hidden_size": 480,
280
+ "dropout": 0,
281
+ "dtype": null,
282
+ "early_stopping": false,
283
+ "encoder_attention_heads": 20,
284
+ "encoder_ffn_dim": 5120,
285
+ "encoder_layers": 32,
286
+ "encoder_no_repeat_ngram_size": 0,
287
+ "eos_token_id": null,
288
+ "exponential_decay_length_penalty": null,
289
+ "finetuning_task": null,
290
+ "forced_bos_token_id": null,
291
+ "forced_eos_token_id": null,
292
+ "id2label": {
293
+ "0": "LABEL_0",
294
+ "1": "LABEL_1"
295
+ },
296
+ "initializer_range": 0.02,
297
+ "is_decoder": false,
298
+ "is_encoder_decoder": false,
299
+ "label2id": {
300
+ "LABEL_0": 0,
301
+ "LABEL_1": 1
302
+ },
303
+ "length_penalty": 1.0,
304
+ "max_length": 20,
305
+ "max_source_positions": 1500,
306
+ "min_length": 0,
307
+ "model_type": "qwen3_omni_moe_audio_encoder",
308
+ "n_window": 50,
309
+ "n_window_infer": 800,
310
+ "no_repeat_ngram_size": 0,
311
+ "num_beam_groups": 1,
312
+ "num_beams": 1,
313
+ "num_hidden_layers": 32,
314
+ "num_mel_bins": 128,
315
+ "num_return_sequences": 1,
316
+ "output_attentions": false,
317
+ "output_dim": 2048,
318
+ "output_hidden_states": false,
319
+ "output_scores": false,
320
+ "pad_token_id": null,
321
+ "prefix": null,
322
+ "problem_type": null,
323
+ "pruned_heads": {},
324
+ "remove_invalid_values": false,
325
+ "repetition_penalty": 1.0,
326
+ "return_dict": true,
327
+ "return_dict_in_generate": false,
328
+ "scale_embedding": false,
329
+ "sep_token_id": null,
330
+ "suppress_tokens": null,
331
+ "task_specific_params": null,
332
+ "temperature": 1.0,
333
+ "tf_legacy_loss": false,
334
+ "tie_encoder_decoder": false,
335
+ "tie_word_embeddings": true,
336
+ "tokenizer_class": null,
337
+ "top_k": 50,
338
+ "top_p": 1.0,
339
+ "torchscript": false,
340
+ "typical_p": 1.0,
341
+ "use_bfloat16": false
342
+ },
343
+ "audio_end_token_id": 151670,
344
+ "audio_start_token_id": 151669,
345
+ "audio_token_id": 151675,
346
+ "dtype": "bfloat16",
347
+ "image_token_id": 151655,
348
+ "initializer_range": 0.02,
349
+ "model_type": "qwen3_omni_moe_thinker",
350
+ "position_id_per_seconds": 13,
351
+ "seconds_per_chunk": 2,
352
+ "text_config": {
353
+ "_name_or_path": "",
354
+ "add_cross_attention": false,
355
+ "architectures": null,
356
+ "attention_bias": false,
357
+ "attention_dropout": 0.0,
358
+ "bad_words_ids": null,
359
+ "begin_suppress_tokens": null,
360
+ "bos_token_id": null,
361
+ "chunk_size_feed_forward": 0,
362
+ "cross_attention_hidden_size": null,
363
+ "decoder_sparse_step": 1,
364
+ "decoder_start_token_id": null,
365
+ "diversity_penalty": 0.0,
366
+ "do_sample": false,
367
+ "dtype": null,
368
+ "early_stopping": false,
369
+ "encoder_no_repeat_ngram_size": 0,
370
+ "eos_token_id": null,
371
+ "exponential_decay_length_penalty": null,
372
+ "finetuning_task": null,
373
+ "forced_bos_token_id": null,
374
+ "forced_eos_token_id": null,
375
+ "head_dim": 128,
376
+ "hidden_act": "silu",
377
+ "hidden_size": 2048,
378
+ "id2label": {
379
+ "0": "LABEL_0",
380
+ "1": "LABEL_1"
381
+ },
382
+ "initializer_range": 0.02,
383
+ "intermediate_size": 768,
384
+ "is_decoder": false,
385
+ "is_encoder_decoder": false,
386
+ "label2id": {
387
+ "LABEL_0": 0,
388
+ "LABEL_1": 1
389
+ },
390
+ "length_penalty": 1.0,
391
+ "max_length": 20,
392
+ "max_position_embeddings": 65536,
393
+ "min_length": 0,
394
+ "mlp_only_layers": [],
395
+ "model_type": "qwen3_omni_moe_text",
396
+ "moe_intermediate_size": 768,
397
+ "no_repeat_ngram_size": 0,
398
+ "norm_topk_prob": true,
399
+ "num_attention_heads": 32,
400
+ "num_beam_groups": 1,
401
+ "num_beams": 1,
402
+ "num_experts": 128,
403
+ "num_experts_per_tok": 8,
404
+ "num_hidden_layers": 48,
405
+ "num_key_value_heads": 4,
406
+ "num_return_sequences": 1,
407
+ "output_attentions": false,
408
+ "output_hidden_states": false,
409
+ "output_router_logits": false,
410
+ "output_scores": false,
411
+ "pad_token_id": null,
412
+ "prefix": null,
413
+ "problem_type": null,
414
+ "pruned_heads": {},
415
+ "remove_invalid_values": false,
416
+ "repetition_penalty": 1.0,
417
+ "return_dict": true,
418
+ "return_dict_in_generate": false,
419
+ "rms_norm_eps": 1e-06,
420
+ "rope_scaling": {
421
+ "interleaved": true,
422
+ "mrope_interleaved": true,
423
+ "mrope_section": [
424
+ 24,
425
+ 20,
426
+ 20
427
+ ],
428
+ "rope_type": "default",
429
+ "type": "default"
430
+ },
431
+ "rope_theta": 1000000,
432
+ "router_aux_loss_coef": 0.001,
433
+ "sep_token_id": null,
434
+ "shared_expert_intermediate_size": 0,
435
+ "sliding_window": null,
436
+ "suppress_tokens": null,
437
+ "task_specific_params": null,
438
+ "temperature": 1.0,
439
+ "tf_legacy_loss": false,
440
+ "tie_encoder_decoder": false,
441
+ "tie_word_embeddings": false,
442
+ "tokenizer_class": null,
443
+ "top_k": 50,
444
+ "top_p": 1.0,
445
+ "torchscript": false,
446
+ "typical_p": 1.0,
447
+ "use_bfloat16": false,
448
+ "use_cache": true,
449
+ "use_qk_norm": true,
450
+ "use_sliding_window": false,
451
+ "vocab_size": 152064
452
+ },
453
+ "user_token_id": 872,
454
+ "video_token_id": 151656,
455
+ "vision_config": {
456
+ "_name_or_path": "",
457
+ "add_cross_attention": false,
458
+ "apply_vit_abs_pos_embed": true,
459
+ "architectures": null,
460
+ "bad_words_ids": null,
461
+ "begin_suppress_tokens": null,
462
+ "bos_token_id": null,
463
+ "chunk_size_feed_forward": 0,
464
+ "cross_attention_hidden_size": null,
465
+ "decoder_start_token_id": null,
466
+ "deepstack_visual_indexes": [
467
+ 8,
468
+ 16,
469
+ 24
470
+ ],
471
+ "depth": 27,
472
+ "diversity_penalty": 0.0,
473
+ "do_sample": false,
474
+ "dtype": null,
475
+ "early_stopping": false,
476
+ "encoder_no_repeat_ngram_size": 0,
477
+ "eos_token_id": null,
478
+ "exponential_decay_length_penalty": null,
479
+ "finetuning_task": null,
480
+ "forced_bos_token_id": null,
481
+ "forced_eos_token_id": null,
482
+ "hidden_act": "gelu_pytorch_tanh",
483
+ "hidden_size": 1152,
484
+ "id2label": {
485
+ "0": "LABEL_0",
486
+ "1": "LABEL_1"
487
+ },
488
+ "image_size": 768,
489
+ "in_channels": 3,
490
+ "in_chans": 3,
491
+ "initializer_range": 0.02,
492
+ "intermediate_size": 4304,
493
+ "is_decoder": false,
494
+ "is_encoder_decoder": false,
495
+ "label2id": {
496
+ "LABEL_0": 0,
497
+ "LABEL_1": 1
498
+ },
499
+ "length_penalty": 1.0,
500
+ "max_length": 20,
501
+ "min_length": 0,
502
+ "model_type": "qwen3_omni_moe_vision_encoder",
503
+ "no_repeat_ngram_size": 0,
504
+ "num_beam_groups": 1,
505
+ "num_beams": 1,
506
+ "num_heads": 16,
507
+ "num_position_embeddings": 2304,
508
+ "num_return_sequences": 1,
509
+ "out_hidden_size": 2048,
510
+ "output_attentions": false,
511
+ "output_hidden_states": false,
512
+ "output_scores": false,
513
+ "pad_token_id": null,
514
+ "patch_size": 16,
515
+ "prefix": null,
516
+ "problem_type": null,
517
+ "pruned_heads": {},
518
+ "remove_invalid_values": false,
519
+ "repetition_penalty": 1.0,
520
+ "return_dict": true,
521
+ "return_dict_in_generate": false,
522
+ "sep_token_id": null,
523
+ "spatial_merge_size": 2,
524
+ "spatial_patch_size": 16,
525
+ "suppress_tokens": null,
526
+ "task_specific_params": null,
527
+ "temperature": 1.0,
528
+ "temporal_patch_size": 2,
529
+ "tf_legacy_loss": false,
530
+ "tie_encoder_decoder": false,
531
+ "tie_word_embeddings": true,
532
+ "tokenizer_class": null,
533
+ "tokens_per_second": 2,
534
+ "top_k": 50,
535
+ "top_p": 1.0,
536
+ "torchscript": false,
537
+ "typical_p": 1.0,
538
+ "use_bfloat16": false
539
+ },
540
+ "vision_end_token_id": 151653,
541
+ "vision_start_token_id": 151652
542
+ },
543
+ "transformers_version": "4.57.1",
544
+ "tts_bos_token_id": 151672,
545
+ "tts_eos_token_id": 151673,
546
+ "tts_pad_token_id": 151671,
547
+ "user_token_id": 872
548
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
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
+ "transformers_version": "4.57.1"
8
+ }
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 sha256:03f754bcbc425fedaccafcdfeaca98a3048474f2d83c9b7d4d5a1929fa735127
3
+ size 4997899632
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ecb861355dac21e0dd09e8f4a9eff6b677ffa3ae1c658881f39a43e5cb730e
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:ff8d60e1ac30a8e1d289eebfa4ca86aca64778ab0e892b98fc95ebb668b5670d
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:a30e580972c5103386941e6910d42c6fbdd09be5626a1543d79da5f0114a3a42
3
+ size 4997755648
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfd2d760e9c96cebe61c4f7a85d0634a3cf473c6c723d4ca62a4dd70b59f21b
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:fd0ee7c2e9fa4d83b03f107bedf4e1fe9a73f2fdd55a36c569d7971d69cdf650
3
+ size 4997755792
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441774c934175f45f1a23fdd47856dbf1e98e16b34380afd2a78eed36e2b4e64
3
+ size 4997755792
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b7c1e4b98ed852fd7b9f592f4c7f243c3ad91a1de25bced3f5496a9a9123ce
3
+ size 4997755792
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea85eff06d23f128ea77c743217d89eff00bb9e489e3ac54e7aeddbb86177fc
3
+ size 4997755792
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b526537c5bac045f66e81e15a1d332ff891d384daa63c67d557d7ba19a0b201
3
+ size 4997755792
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8933ff5e4c1dc068e63018ee18915a3490708995a1ca639d7abd6a31f9c24692
3
+ size 4997755792
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c062ab458cfc7d1564fba82459f8f9f3929af6f4c759412a3bd3697ac16f28
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:d5e43fcd92dc429dfc3388cc97da28576051a7a4f3ebdacad8957e301d49b2ee
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
+ }
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 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "split_special_tokens": false,
311
+ "tokenizer_class": "Qwen2Tokenizer",
312
+ "unk_token": null,
313
+ "video_token": "<|video_pad|>",
314
+ "vision_bos_token": "<|vision_start|>",
315
+ "vision_eos_token": "<|vision_end|>"
316
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff