Instructions to use OpenFormosa/PangolinTokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenFormosa/PangolinTokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenFormosa/PangolinTokenizer", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add Open Formosa special tokens
Browse files- README.md +12 -32
- added_tokens.json +171 -0
- evaluation_report.json +19 -53
- special_tokens_map.json +140 -6
- tokenizer.json +1209 -3
- tokenizer_config.json +162 -12
README.md
CHANGED
|
@@ -11,8 +11,12 @@ tags:
|
|
| 11 |
|
| 12 |
# PangolinTokenizer
|
| 13 |
|
| 14 |
-
Byte-level BPE tokenizer
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Usage
|
| 18 |
|
|
@@ -29,36 +33,12 @@ ids = tokenizer.encode(text)
|
|
| 29 |
decoded = tokenizer.decode(ids)
|
| 30 |
```
|
| 31 |
|
| 32 |
-
##
|
| 33 |
-
|
| 34 |
-
- `config.json`
|
| 35 |
-
- `tokenizer_config.json`
|
| 36 |
-
- `tokenizer.json`
|
| 37 |
-
- `vocab.json`
|
| 38 |
-
- `merges.txt`
|
| 39 |
-
- `special_tokens_map.json`
|
| 40 |
-
- `evaluation_report.json`
|
| 41 |
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
-
|
| 45 |
-
- Vocabulary size: 114,688
|
| 46 |
-
- Learned merges: 114,397
|
| 47 |
- Model max length metadata: 131,072
|
| 48 |
-
- Minimum merge frequency: 5
|
| 49 |
-
- Transformers class: `GPT2TokenizerFast`
|
| 50 |
- `trust_remote_code`: not required
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
This tokenizer intentionally does not include discrete audio codec token ranges.
|
| 55 |
-
It also intentionally does not include dense timestamp token ranges. Audio should
|
| 56 |
-
be represented through external references or embeddings outside this tokenizer.
|
| 57 |
-
|
| 58 |
-
Evaluation checks confirmed:
|
| 59 |
-
|
| 60 |
-
- Transformers `AutoTokenizer` loading works with `trust_remote_code=False`
|
| 61 |
-
- Traditional Chinese and Bopomofo smoke roundtrip works
|
| 62 |
-
- No tokens matching `<|audio_[0-9]+|>`
|
| 63 |
-
- No dense timestamp token ranges matching `<|ts_[0-9]+|>`,
|
| 64 |
-
`<|timestamp_[0-9]+|>`, or `<|time_[0-9]+|>`
|
|
|
|
| 11 |
|
| 12 |
# PangolinTokenizer
|
| 13 |
|
| 14 |
+
Byte-level BPE tokenizer for Traditional Chinese, Taiwan text, multilingual text,
|
| 15 |
+
rich transcription, OCR-style text, and generic control formats.
|
| 16 |
+
|
| 17 |
+
This revision adds the Open Formosa required control tokens as special tokens.
|
| 18 |
+
The base BPE vocabulary size remains 114,688. The effective tokenizer length,
|
| 19 |
+
including added special tokens, is 114,822.
|
| 20 |
|
| 21 |
## Usage
|
| 22 |
|
|
|
|
| 33 |
decoded = tokenizer.decode(ids)
|
| 34 |
```
|
| 35 |
|
| 36 |
+
## Open Formosa Compatibility
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
+
- Required special tokens present: 157
|
| 39 |
+
- Required special tokens encode as single IDs: yes
|
| 40 |
+
- Standard special tokens: `<unk>`, `<s>`, `</s>`, `<pad>`
|
|
|
|
|
|
|
| 41 |
- Model max length metadata: 131,072
|
|
|
|
|
|
|
| 42 |
- `trust_remote_code`: not required
|
| 43 |
+
- No discrete audio codec token ranges are included.
|
| 44 |
+
- No dense timestamp token ranges are included.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
added_tokens.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|pad|>": 114653,
|
| 3 |
+
"<|bos|>": 114654,
|
| 4 |
+
"<|eos|>": 114655,
|
| 5 |
+
"<|unk|>": 114656,
|
| 6 |
+
"<|system|>": 114657,
|
| 7 |
+
"<|user_channel|>": 114658,
|
| 8 |
+
"<|assistant_channel|>": 114659,
|
| 9 |
+
"<|task:speech_to_text|>": 114660,
|
| 10 |
+
"<|task:text_to_speech|>": 114661,
|
| 11 |
+
"<|input_audio_start|>": 114662,
|
| 12 |
+
"<|input_audio_end|>": 114663,
|
| 13 |
+
"<|audio_ref_start|>": 114664,
|
| 14 |
+
"<|audio_ref_end|>": 114665,
|
| 15 |
+
"<|audio_start|>": 114666,
|
| 16 |
+
"<|audio_end|>": 114667,
|
| 17 |
+
"<|speech_start|>": 114668,
|
| 18 |
+
"<|speech_end|>": 114669,
|
| 19 |
+
"<|transcript_start|>": 114670,
|
| 20 |
+
"<|transcript_end|>": 114671,
|
| 21 |
+
"<|segment_start|>": 114672,
|
| 22 |
+
"<|segment_end|>": 114673,
|
| 23 |
+
"<|speaker|>": 114674,
|
| 24 |
+
"<|start_time|>": 114675,
|
| 25 |
+
"<|end_time|>": 114676,
|
| 26 |
+
"<|duration|>": 114677,
|
| 27 |
+
"<|content|>": 114678,
|
| 28 |
+
"<|non_speech_event|>": 114679,
|
| 29 |
+
"<|retrieval_result_start|>": 114680,
|
| 30 |
+
"<|retrieval_result_end|>": 114681,
|
| 31 |
+
"<|ocr_start|>": 114682,
|
| 32 |
+
"<|ocr_end|>": 114683,
|
| 33 |
+
"<|image_start|>": 114684,
|
| 34 |
+
"<|image_end|>": 114685,
|
| 35 |
+
"<|video_start|>": 114686,
|
| 36 |
+
"<|video_end|>": 114687,
|
| 37 |
+
"<unk>": 114688,
|
| 38 |
+
"<s>": 114689,
|
| 39 |
+
"</s>": 114690,
|
| 40 |
+
"<pad>": 114691,
|
| 41 |
+
"<|user|>": 114692,
|
| 42 |
+
"<|assistant|>": 114693,
|
| 43 |
+
"<|tool_call|>": 114694,
|
| 44 |
+
"<|tool_response|>": 114695,
|
| 45 |
+
"<|endoftext|>": 114696,
|
| 46 |
+
"<think>": 114697,
|
| 47 |
+
"</think>": 114698,
|
| 48 |
+
"<|no_think|>": 114699,
|
| 49 |
+
"<|think|>": 114700,
|
| 50 |
+
"<|think_max|>": 114701,
|
| 51 |
+
"<|task:text_to_text|>": 114702,
|
| 52 |
+
"<|task:speech_to_speech|>": 114703,
|
| 53 |
+
"<|task:text_speech_to_text|>": 114704,
|
| 54 |
+
"<|task:text_speech_to_speech|>": 114705,
|
| 55 |
+
"<|task:full_duplex_speech|>": 114706,
|
| 56 |
+
"<|task:agent|>": 114707,
|
| 57 |
+
"<|task:tool_use|>": 114708,
|
| 58 |
+
"<|task:rag|>": 114709,
|
| 59 |
+
"<|task:code_execution|>": 114710,
|
| 60 |
+
"<|task:document_qa|>": 114711,
|
| 61 |
+
"<|task:data_analysis|>": 114712,
|
| 62 |
+
"<|task:workflow|>": 114713,
|
| 63 |
+
"<|reasoning_mode:none|>": 114714,
|
| 64 |
+
"<|reasoning_mode:short|>": 114715,
|
| 65 |
+
"<|reasoning_mode:deep|>": 114716,
|
| 66 |
+
"<|reasoning_mode:verify|>": 114717,
|
| 67 |
+
"<|private_reasoning_start|>": 114718,
|
| 68 |
+
"<|private_reasoning_end|>": 114719,
|
| 69 |
+
"<|reasoning_summary_start|>": 114720,
|
| 70 |
+
"<|reasoning_summary_end|>": 114721,
|
| 71 |
+
"<|plan_start|>": 114722,
|
| 72 |
+
"<|plan_end|>": 114723,
|
| 73 |
+
"<|step_start|>": 114724,
|
| 74 |
+
"<|step_end|>": 114725,
|
| 75 |
+
"<|action_start|>": 114726,
|
| 76 |
+
"<|action_end|>": 114727,
|
| 77 |
+
"<|observation_start|>": 114728,
|
| 78 |
+
"<|observation_end|>": 114729,
|
| 79 |
+
"<|reflection_start|>": 114730,
|
| 80 |
+
"<|reflection_end|>": 114731,
|
| 81 |
+
"<|verification_start|>": 114732,
|
| 82 |
+
"<|verification_end|>": 114733,
|
| 83 |
+
"<|tool_schema_start|>": 114734,
|
| 84 |
+
"<|tool_schema_end|>": 114735,
|
| 85 |
+
"<|tool_call_start|>": 114736,
|
| 86 |
+
"<|tool_call_end|>": 114737,
|
| 87 |
+
"<|tool_result_start|>": 114738,
|
| 88 |
+
"<|tool_result_end|>": 114739,
|
| 89 |
+
"<|tool_error_start|>": 114740,
|
| 90 |
+
"<|tool_error_end|>": 114741,
|
| 91 |
+
"<|retrieval_query_start|>": 114742,
|
| 92 |
+
"<|retrieval_query_end|>": 114743,
|
| 93 |
+
"<|citation_start|>": 114744,
|
| 94 |
+
"<|citation_end|>": 114745,
|
| 95 |
+
"<|memory_read_start|>": 114746,
|
| 96 |
+
"<|memory_read_end|>": 114747,
|
| 97 |
+
"<|memory_write_start|>": 114748,
|
| 98 |
+
"<|memory_write_end|>": 114749,
|
| 99 |
+
"<|final_answer_start|>": 114750,
|
| 100 |
+
"<|final_answer_end|>": 114751,
|
| 101 |
+
"<|json_start|>": 114752,
|
| 102 |
+
"<|json_end|>": 114753,
|
| 103 |
+
"<|code_start|>": 114754,
|
| 104 |
+
"<|code_end|>": 114755,
|
| 105 |
+
"<|markdown_start|>": 114756,
|
| 106 |
+
"<|markdown_end|>": 114757,
|
| 107 |
+
"<|duplex_start|>": 114758,
|
| 108 |
+
"<|duplex_end|>": 114759,
|
| 109 |
+
"<|system_channel|>": 114760,
|
| 110 |
+
"<|listen|>": 114761,
|
| 111 |
+
"<|speak|>": 114762,
|
| 112 |
+
"<|listen_speak|>": 114763,
|
| 113 |
+
"<|output_audio_start|>": 114764,
|
| 114 |
+
"<|output_audio_end|>": 114765,
|
| 115 |
+
"<|text_start|>": 114766,
|
| 116 |
+
"<|text_end|>": 114767,
|
| 117 |
+
"<|overlap|>": 114768,
|
| 118 |
+
"<|barge_in|>": 114769,
|
| 119 |
+
"<|interruption|>": 114770,
|
| 120 |
+
"<|interruption_repair|>": 114771,
|
| 121 |
+
"<|backchannel|>": 114772,
|
| 122 |
+
"<|turn_yield|>": 114773,
|
| 123 |
+
"<|hold|>": 114774,
|
| 124 |
+
"<|silence|>": 114775,
|
| 125 |
+
"<|non_speech|>": 114776,
|
| 126 |
+
"<|voice_reference_start|>": 114777,
|
| 127 |
+
"<|voice_reference_end|>": 114778,
|
| 128 |
+
"<|voice_reference|>": 114779,
|
| 129 |
+
"<|voice_switch|>": 114780,
|
| 130 |
+
"<|speaker_style|>": 114781,
|
| 131 |
+
"<|prosody_control|>": 114782,
|
| 132 |
+
"<|zh_tw|>": 114783,
|
| 133 |
+
"<|zh_hant|>": 114784,
|
| 134 |
+
"<|taigi|>": 114785,
|
| 135 |
+
"<|hakka|>": 114786,
|
| 136 |
+
"<|bopomofo|>": 114787,
|
| 137 |
+
"<|mixed_en|>": 114788,
|
| 138 |
+
"<|en|>": 114789,
|
| 139 |
+
"<|ja|>": 114790,
|
| 140 |
+
"<|ko|>": 114791,
|
| 141 |
+
"<|vi|>": 114792,
|
| 142 |
+
"<|id|>": 114793,
|
| 143 |
+
"<|th|>": 114794,
|
| 144 |
+
"<|asr|>": 114795,
|
| 145 |
+
"<|tts|>": 114796,
|
| 146 |
+
"<|speaker_0|>": 114797,
|
| 147 |
+
"<|speaker_1|>": 114798,
|
| 148 |
+
"<|speaker_2|>": 114799,
|
| 149 |
+
"<|speaker_3|>": 114800,
|
| 150 |
+
"<|timestamp|>": 114801,
|
| 151 |
+
"<|noise|>": 114802,
|
| 152 |
+
"<|laugh|>": 114803,
|
| 153 |
+
"<|breath|>": 114804,
|
| 154 |
+
"<|pause|>": 114805,
|
| 155 |
+
"<|prosody|>": 114806,
|
| 156 |
+
"<|pron|>": 114807,
|
| 157 |
+
"</|pron|>": 114808,
|
| 158 |
+
"<|image|>": 114809,
|
| 159 |
+
"<|ocr|>": 114810,
|
| 160 |
+
"<|bbox|>": 114811,
|
| 161 |
+
"<|line|>": 114812,
|
| 162 |
+
"<|table|>": 114813,
|
| 163 |
+
"<|row|>": 114814,
|
| 164 |
+
"<|col|>": 114815,
|
| 165 |
+
"<|cell|>": 114816,
|
| 166 |
+
"<|reading_order|>": 114817,
|
| 167 |
+
"<|source|>": 114818,
|
| 168 |
+
"<|cite|>": 114819,
|
| 169 |
+
"<|evidence|>": 114820,
|
| 170 |
+
"<|quote|>": 114821
|
| 171 |
+
}
|
evaluation_report.json
CHANGED
|
@@ -1,58 +1,24 @@
|
|
| 1 |
{
|
| 2 |
"ok": true,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
"<|duration|>": 114677,
|
| 15 |
-
"<|content|>": 114678,
|
| 16 |
-
"<|non_speech_event|>": 114679
|
| 17 |
-
},
|
| 18 |
-
"timestamp_precision_digits": 2,
|
| 19 |
-
"json_roundtrip_ok": true,
|
| 20 |
-
"dense_timestamp_tokens_found": [],
|
| 21 |
-
"missing_rich_transcription_tokens": [],
|
| 22 |
-
"timestamp_strings_present": {
|
| 23 |
-
"0.00": true,
|
| 24 |
-
"3.42": true,
|
| 25 |
-
"10.25": true,
|
| 26 |
-
"3575.50": true
|
| 27 |
-
},
|
| 28 |
-
"non_speech_labels_present": {
|
| 29 |
-
"[Silence]": true,
|
| 30 |
-
"[Noise]": true,
|
| 31 |
-
"[Music]": true,
|
| 32 |
-
"[Unintelligible Speech]": true
|
| 33 |
-
},
|
| 34 |
-
"text_roundtrip_ok": {
|
| 35 |
-
"traditional_chinese": true,
|
| 36 |
-
"bopomofo_mixed_romanization": true,
|
| 37 |
-
"json_syntax": true
|
| 38 |
-
},
|
| 39 |
-
"required_fields_ok": true,
|
| 40 |
-
"parse_error": null
|
| 41 |
-
}
|
| 42 |
},
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"<|segment_start|>": 114672,
|
| 47 |
-
"<|segment_end|>": 114673,
|
| 48 |
-
"<|speaker|>": 114674,
|
| 49 |
-
"<|start_time|>": 114675,
|
| 50 |
-
"<|end_time|>": 114676,
|
| 51 |
-
"<|duration|>": 114677,
|
| 52 |
-
"<|content|>": 114678,
|
| 53 |
-
"<|non_speech_event|>": 114679
|
| 54 |
},
|
| 55 |
-
"
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
| 58 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"ok": true,
|
| 3 |
+
"tokenizer": "voidful/PangolinTokenizer",
|
| 4 |
+
"base_vocab_size": 114688,
|
| 5 |
+
"effective_vocab_size": 114822,
|
| 6 |
+
"required_special_token_count": 157,
|
| 7 |
+
"required_special_tokens_missing": [],
|
| 8 |
+
"required_special_tokens_single_id": true,
|
| 9 |
+
"standard_special_tokens": {
|
| 10 |
+
"bos_token": "<s>",
|
| 11 |
+
"eos_token": "</s>",
|
| 12 |
+
"unk_token": "<unk>",
|
| 13 |
+
"pad_token": "<pad>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
},
|
| 15 |
+
"banned_token_matches": {
|
| 16 |
+
"audio_numeric_tokens": [],
|
| 17 |
+
"dense_timestamp_tokens": []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
},
|
| 19 |
+
"smoke_texts": {
|
| 20 |
+
"traditional_chinese": "台灣本土語言模型需要保留繁體中文、注音ㄅㄆㄇ與台語漢字。",
|
| 21 |
+
"duplex": "<|task:full_duplex_speech|><|audio_ref_start|>audio://utterance_000001<|audio_ref_end|>",
|
| 22 |
+
"tool_call": "<|tool_call_start|>{\"name\":\"search_documents\",\"arguments\":{\"query\":\"健保年金\"}}<|tool_call_end|>"
|
| 23 |
+
}
|
| 24 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,13 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"<|system|>",
|
| 4 |
"<|user_channel|>",
|
| 5 |
"<|assistant_channel|>",
|
|
@@ -30,10 +38,136 @@
|
|
| 30 |
"<|image_start|>",
|
| 31 |
"<|image_end|>",
|
| 32 |
"<|video_start|>",
|
| 33 |
-
"<|video_end|>"
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
"additional_special_tokens": [
|
| 7 |
+
"<|bos|>",
|
| 8 |
+
"<|eos|>",
|
| 9 |
+
"<|unk|>",
|
| 10 |
+
"<|pad|>",
|
| 11 |
"<|system|>",
|
| 12 |
"<|user_channel|>",
|
| 13 |
"<|assistant_channel|>",
|
|
|
|
| 38 |
"<|image_start|>",
|
| 39 |
"<|image_end|>",
|
| 40 |
"<|video_start|>",
|
| 41 |
+
"<|video_end|>",
|
| 42 |
+
"<|user|>",
|
| 43 |
+
"<|assistant|>",
|
| 44 |
+
"<|tool_call|>",
|
| 45 |
+
"<|tool_response|>",
|
| 46 |
+
"<|endoftext|>",
|
| 47 |
+
"<think>",
|
| 48 |
+
"</think>",
|
| 49 |
+
"<|no_think|>",
|
| 50 |
+
"<|think|>",
|
| 51 |
+
"<|think_max|>",
|
| 52 |
+
"<|task:text_to_text|>",
|
| 53 |
+
"<|task:speech_to_speech|>",
|
| 54 |
+
"<|task:text_speech_to_text|>",
|
| 55 |
+
"<|task:text_speech_to_speech|>",
|
| 56 |
+
"<|task:full_duplex_speech|>",
|
| 57 |
+
"<|task:agent|>",
|
| 58 |
+
"<|task:tool_use|>",
|
| 59 |
+
"<|task:rag|>",
|
| 60 |
+
"<|task:code_execution|>",
|
| 61 |
+
"<|task:document_qa|>",
|
| 62 |
+
"<|task:data_analysis|>",
|
| 63 |
+
"<|task:workflow|>",
|
| 64 |
+
"<|reasoning_mode:none|>",
|
| 65 |
+
"<|reasoning_mode:short|>",
|
| 66 |
+
"<|reasoning_mode:deep|>",
|
| 67 |
+
"<|reasoning_mode:verify|>",
|
| 68 |
+
"<|private_reasoning_start|>",
|
| 69 |
+
"<|private_reasoning_end|>",
|
| 70 |
+
"<|reasoning_summary_start|>",
|
| 71 |
+
"<|reasoning_summary_end|>",
|
| 72 |
+
"<|plan_start|>",
|
| 73 |
+
"<|plan_end|>",
|
| 74 |
+
"<|step_start|>",
|
| 75 |
+
"<|step_end|>",
|
| 76 |
+
"<|action_start|>",
|
| 77 |
+
"<|action_end|>",
|
| 78 |
+
"<|observation_start|>",
|
| 79 |
+
"<|observation_end|>",
|
| 80 |
+
"<|reflection_start|>",
|
| 81 |
+
"<|reflection_end|>",
|
| 82 |
+
"<|verification_start|>",
|
| 83 |
+
"<|verification_end|>",
|
| 84 |
+
"<|tool_schema_start|>",
|
| 85 |
+
"<|tool_schema_end|>",
|
| 86 |
+
"<|tool_call_start|>",
|
| 87 |
+
"<|tool_call_end|>",
|
| 88 |
+
"<|tool_result_start|>",
|
| 89 |
+
"<|tool_result_end|>",
|
| 90 |
+
"<|tool_error_start|>",
|
| 91 |
+
"<|tool_error_end|>",
|
| 92 |
+
"<|retrieval_query_start|>",
|
| 93 |
+
"<|retrieval_query_end|>",
|
| 94 |
+
"<|citation_start|>",
|
| 95 |
+
"<|citation_end|>",
|
| 96 |
+
"<|memory_read_start|>",
|
| 97 |
+
"<|memory_read_end|>",
|
| 98 |
+
"<|memory_write_start|>",
|
| 99 |
+
"<|memory_write_end|>",
|
| 100 |
+
"<|final_answer_start|>",
|
| 101 |
+
"<|final_answer_end|>",
|
| 102 |
+
"<|json_start|>",
|
| 103 |
+
"<|json_end|>",
|
| 104 |
+
"<|code_start|>",
|
| 105 |
+
"<|code_end|>",
|
| 106 |
+
"<|markdown_start|>",
|
| 107 |
+
"<|markdown_end|>",
|
| 108 |
+
"<|duplex_start|>",
|
| 109 |
+
"<|duplex_end|>",
|
| 110 |
+
"<|system_channel|>",
|
| 111 |
+
"<|listen|>",
|
| 112 |
+
"<|speak|>",
|
| 113 |
+
"<|listen_speak|>",
|
| 114 |
+
"<|output_audio_start|>",
|
| 115 |
+
"<|output_audio_end|>",
|
| 116 |
+
"<|text_start|>",
|
| 117 |
+
"<|text_end|>",
|
| 118 |
+
"<|overlap|>",
|
| 119 |
+
"<|barge_in|>",
|
| 120 |
+
"<|interruption|>",
|
| 121 |
+
"<|interruption_repair|>",
|
| 122 |
+
"<|backchannel|>",
|
| 123 |
+
"<|turn_yield|>",
|
| 124 |
+
"<|hold|>",
|
| 125 |
+
"<|silence|>",
|
| 126 |
+
"<|non_speech|>",
|
| 127 |
+
"<|voice_reference_start|>",
|
| 128 |
+
"<|voice_reference_end|>",
|
| 129 |
+
"<|voice_reference|>",
|
| 130 |
+
"<|voice_switch|>",
|
| 131 |
+
"<|speaker_style|>",
|
| 132 |
+
"<|prosody_control|>",
|
| 133 |
+
"<|zh_tw|>",
|
| 134 |
+
"<|zh_hant|>",
|
| 135 |
+
"<|taigi|>",
|
| 136 |
+
"<|hakka|>",
|
| 137 |
+
"<|bopomofo|>",
|
| 138 |
+
"<|mixed_en|>",
|
| 139 |
+
"<|en|>",
|
| 140 |
+
"<|ja|>",
|
| 141 |
+
"<|ko|>",
|
| 142 |
+
"<|vi|>",
|
| 143 |
+
"<|id|>",
|
| 144 |
+
"<|th|>",
|
| 145 |
+
"<|asr|>",
|
| 146 |
+
"<|tts|>",
|
| 147 |
+
"<|speaker_0|>",
|
| 148 |
+
"<|speaker_1|>",
|
| 149 |
+
"<|speaker_2|>",
|
| 150 |
+
"<|speaker_3|>",
|
| 151 |
+
"<|timestamp|>",
|
| 152 |
+
"<|noise|>",
|
| 153 |
+
"<|laugh|>",
|
| 154 |
+
"<|breath|>",
|
| 155 |
+
"<|pause|>",
|
| 156 |
+
"<|prosody|>",
|
| 157 |
+
"<|pron|>",
|
| 158 |
+
"</|pron|>",
|
| 159 |
+
"<|image|>",
|
| 160 |
+
"<|ocr|>",
|
| 161 |
+
"<|bbox|>",
|
| 162 |
+
"<|line|>",
|
| 163 |
+
"<|table|>",
|
| 164 |
+
"<|row|>",
|
| 165 |
+
"<|col|>",
|
| 166 |
+
"<|cell|>",
|
| 167 |
+
"<|reading_order|>",
|
| 168 |
+
"<|source|>",
|
| 169 |
+
"<|cite|>",
|
| 170 |
+
"<|evidence|>",
|
| 171 |
+
"<|quote|>"
|
| 172 |
+
]
|
| 173 |
}
|
tokenizer.json
CHANGED
|
@@ -317,6 +317,1212 @@
|
|
| 317 |
"rstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 320 |
}
|
| 321 |
],
|
| 322 |
"normalizer": null,
|
|
@@ -361,9 +1567,9 @@
|
|
| 361 |
"model": {
|
| 362 |
"type": "BPE",
|
| 363 |
"dropout": null,
|
| 364 |
-
"unk_token":
|
| 365 |
-
"continuing_subword_prefix":
|
| 366 |
-
"end_of_word_suffix":
|
| 367 |
"fuse_unk": false,
|
| 368 |
"byte_fallback": false,
|
| 369 |
"ignore_merges": false,
|
|
|
|
| 317 |
"rstrip": false,
|
| 318 |
"normalized": false,
|
| 319 |
"special": true
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"id": 114688,
|
| 323 |
+
"content": "<unk>",
|
| 324 |
+
"single_word": false,
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"rstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"special": true
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"id": 114689,
|
| 332 |
+
"content": "<s>",
|
| 333 |
+
"single_word": false,
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"id": 114690,
|
| 341 |
+
"content": "</s>",
|
| 342 |
+
"single_word": false,
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"id": 114691,
|
| 350 |
+
"content": "<pad>",
|
| 351 |
+
"single_word": false,
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"normalized": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"id": 114692,
|
| 359 |
+
"content": "<|user|>",
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"lstrip": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"normalized": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"id": 114693,
|
| 368 |
+
"content": "<|assistant|>",
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"lstrip": false,
|
| 371 |
+
"rstrip": false,
|
| 372 |
+
"normalized": false,
|
| 373 |
+
"special": true
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"id": 114694,
|
| 377 |
+
"content": "<|tool_call|>",
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"lstrip": false,
|
| 380 |
+
"rstrip": false,
|
| 381 |
+
"normalized": false,
|
| 382 |
+
"special": true
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"id": 114695,
|
| 386 |
+
"content": "<|tool_response|>",
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"lstrip": false,
|
| 389 |
+
"rstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"special": true
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"id": 114696,
|
| 395 |
+
"content": "<|endoftext|>",
|
| 396 |
+
"single_word": false,
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"rstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"special": true
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"id": 114697,
|
| 404 |
+
"content": "<think>",
|
| 405 |
+
"single_word": false,
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"id": 114698,
|
| 413 |
+
"content": "</think>",
|
| 414 |
+
"single_word": false,
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"id": 114699,
|
| 422 |
+
"content": "<|no_think|>",
|
| 423 |
+
"single_word": false,
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"normalized": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"id": 114700,
|
| 431 |
+
"content": "<|think|>",
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"lstrip": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"normalized": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"id": 114701,
|
| 440 |
+
"content": "<|think_max|>",
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"lstrip": false,
|
| 443 |
+
"rstrip": false,
|
| 444 |
+
"normalized": false,
|
| 445 |
+
"special": true
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"id": 114702,
|
| 449 |
+
"content": "<|task:text_to_text|>",
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"lstrip": false,
|
| 452 |
+
"rstrip": false,
|
| 453 |
+
"normalized": false,
|
| 454 |
+
"special": true
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"id": 114703,
|
| 458 |
+
"content": "<|task:speech_to_speech|>",
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"lstrip": false,
|
| 461 |
+
"rstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"special": true
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"id": 114704,
|
| 467 |
+
"content": "<|task:text_speech_to_text|>",
|
| 468 |
+
"single_word": false,
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"rstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"special": true
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"id": 114705,
|
| 476 |
+
"content": "<|task:text_speech_to_speech|>",
|
| 477 |
+
"single_word": false,
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"id": 114706,
|
| 485 |
+
"content": "<|task:full_duplex_speech|>",
|
| 486 |
+
"single_word": false,
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"id": 114707,
|
| 494 |
+
"content": "<|task:agent|>",
|
| 495 |
+
"single_word": false,
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"normalized": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"id": 114708,
|
| 503 |
+
"content": "<|task:tool_use|>",
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"lstrip": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"normalized": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"id": 114709,
|
| 512 |
+
"content": "<|task:rag|>",
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"lstrip": false,
|
| 515 |
+
"rstrip": false,
|
| 516 |
+
"normalized": false,
|
| 517 |
+
"special": true
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"id": 114710,
|
| 521 |
+
"content": "<|task:code_execution|>",
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"lstrip": false,
|
| 524 |
+
"rstrip": false,
|
| 525 |
+
"normalized": false,
|
| 526 |
+
"special": true
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"id": 114711,
|
| 530 |
+
"content": "<|task:document_qa|>",
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"lstrip": false,
|
| 533 |
+
"rstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"special": true
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"id": 114712,
|
| 539 |
+
"content": "<|task:data_analysis|>",
|
| 540 |
+
"single_word": false,
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"rstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"special": true
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"id": 114713,
|
| 548 |
+
"content": "<|task:workflow|>",
|
| 549 |
+
"single_word": false,
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"id": 114714,
|
| 557 |
+
"content": "<|reasoning_mode:none|>",
|
| 558 |
+
"single_word": false,
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"id": 114715,
|
| 566 |
+
"content": "<|reasoning_mode:short|>",
|
| 567 |
+
"single_word": false,
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"normalized": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"id": 114716,
|
| 575 |
+
"content": "<|reasoning_mode:deep|>",
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"lstrip": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"normalized": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"id": 114717,
|
| 584 |
+
"content": "<|reasoning_mode:verify|>",
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"lstrip": false,
|
| 587 |
+
"rstrip": false,
|
| 588 |
+
"normalized": false,
|
| 589 |
+
"special": true
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"id": 114718,
|
| 593 |
+
"content": "<|private_reasoning_start|>",
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"lstrip": false,
|
| 596 |
+
"rstrip": false,
|
| 597 |
+
"normalized": false,
|
| 598 |
+
"special": true
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"id": 114719,
|
| 602 |
+
"content": "<|private_reasoning_end|>",
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"lstrip": false,
|
| 605 |
+
"rstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"special": true
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"id": 114720,
|
| 611 |
+
"content": "<|reasoning_summary_start|>",
|
| 612 |
+
"single_word": false,
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"rstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"special": true
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"id": 114721,
|
| 620 |
+
"content": "<|reasoning_summary_end|>",
|
| 621 |
+
"single_word": false,
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"id": 114722,
|
| 629 |
+
"content": "<|plan_start|>",
|
| 630 |
+
"single_word": false,
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"id": 114723,
|
| 638 |
+
"content": "<|plan_end|>",
|
| 639 |
+
"single_word": false,
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"normalized": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"id": 114724,
|
| 647 |
+
"content": "<|step_start|>",
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"lstrip": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"normalized": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"id": 114725,
|
| 656 |
+
"content": "<|step_end|>",
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"lstrip": false,
|
| 659 |
+
"rstrip": false,
|
| 660 |
+
"normalized": false,
|
| 661 |
+
"special": true
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"id": 114726,
|
| 665 |
+
"content": "<|action_start|>",
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"lstrip": false,
|
| 668 |
+
"rstrip": false,
|
| 669 |
+
"normalized": false,
|
| 670 |
+
"special": true
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"id": 114727,
|
| 674 |
+
"content": "<|action_end|>",
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"lstrip": false,
|
| 677 |
+
"rstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"special": true
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"id": 114728,
|
| 683 |
+
"content": "<|observation_start|>",
|
| 684 |
+
"single_word": false,
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"rstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"special": true
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"id": 114729,
|
| 692 |
+
"content": "<|observation_end|>",
|
| 693 |
+
"single_word": false,
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"id": 114730,
|
| 701 |
+
"content": "<|reflection_start|>",
|
| 702 |
+
"single_word": false,
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"id": 114731,
|
| 710 |
+
"content": "<|reflection_end|>",
|
| 711 |
+
"single_word": false,
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"normalized": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"id": 114732,
|
| 719 |
+
"content": "<|verification_start|>",
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"lstrip": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"normalized": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"id": 114733,
|
| 728 |
+
"content": "<|verification_end|>",
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"lstrip": false,
|
| 731 |
+
"rstrip": false,
|
| 732 |
+
"normalized": false,
|
| 733 |
+
"special": true
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"id": 114734,
|
| 737 |
+
"content": "<|tool_schema_start|>",
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"lstrip": false,
|
| 740 |
+
"rstrip": false,
|
| 741 |
+
"normalized": false,
|
| 742 |
+
"special": true
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"id": 114735,
|
| 746 |
+
"content": "<|tool_schema_end|>",
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"lstrip": false,
|
| 749 |
+
"rstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"special": true
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"id": 114736,
|
| 755 |
+
"content": "<|tool_call_start|>",
|
| 756 |
+
"single_word": false,
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"rstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"special": true
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"id": 114737,
|
| 764 |
+
"content": "<|tool_call_end|>",
|
| 765 |
+
"single_word": false,
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"id": 114738,
|
| 773 |
+
"content": "<|tool_result_start|>",
|
| 774 |
+
"single_word": false,
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"id": 114739,
|
| 782 |
+
"content": "<|tool_result_end|>",
|
| 783 |
+
"single_word": false,
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"normalized": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"id": 114740,
|
| 791 |
+
"content": "<|tool_error_start|>",
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"lstrip": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"normalized": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"id": 114741,
|
| 800 |
+
"content": "<|tool_error_end|>",
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"lstrip": false,
|
| 803 |
+
"rstrip": false,
|
| 804 |
+
"normalized": false,
|
| 805 |
+
"special": true
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"id": 114742,
|
| 809 |
+
"content": "<|retrieval_query_start|>",
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"lstrip": false,
|
| 812 |
+
"rstrip": false,
|
| 813 |
+
"normalized": false,
|
| 814 |
+
"special": true
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"id": 114743,
|
| 818 |
+
"content": "<|retrieval_query_end|>",
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"lstrip": false,
|
| 821 |
+
"rstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"special": true
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"id": 114744,
|
| 827 |
+
"content": "<|citation_start|>",
|
| 828 |
+
"single_word": false,
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"rstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"special": true
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"id": 114745,
|
| 836 |
+
"content": "<|citation_end|>",
|
| 837 |
+
"single_word": false,
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"id": 114746,
|
| 845 |
+
"content": "<|memory_read_start|>",
|
| 846 |
+
"single_word": false,
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"special": true
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"id": 114747,
|
| 854 |
+
"content": "<|memory_read_end|>",
|
| 855 |
+
"single_word": false,
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"normalized": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"id": 114748,
|
| 863 |
+
"content": "<|memory_write_start|>",
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"lstrip": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"normalized": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"id": 114749,
|
| 872 |
+
"content": "<|memory_write_end|>",
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"lstrip": false,
|
| 875 |
+
"rstrip": false,
|
| 876 |
+
"normalized": false,
|
| 877 |
+
"special": true
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"id": 114750,
|
| 881 |
+
"content": "<|final_answer_start|>",
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"lstrip": false,
|
| 884 |
+
"rstrip": false,
|
| 885 |
+
"normalized": false,
|
| 886 |
+
"special": true
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"id": 114751,
|
| 890 |
+
"content": "<|final_answer_end|>",
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"lstrip": false,
|
| 893 |
+
"rstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"special": true
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"id": 114752,
|
| 899 |
+
"content": "<|json_start|>",
|
| 900 |
+
"single_word": false,
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"rstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"special": true
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"id": 114753,
|
| 908 |
+
"content": "<|json_end|>",
|
| 909 |
+
"single_word": false,
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"id": 114754,
|
| 917 |
+
"content": "<|code_start|>",
|
| 918 |
+
"single_word": false,
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"special": true
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"id": 114755,
|
| 926 |
+
"content": "<|code_end|>",
|
| 927 |
+
"single_word": false,
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"normalized": false,
|
| 931 |
+
"special": true
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"id": 114756,
|
| 935 |
+
"content": "<|markdown_start|>",
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"lstrip": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"normalized": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"id": 114757,
|
| 944 |
+
"content": "<|markdown_end|>",
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"lstrip": false,
|
| 947 |
+
"rstrip": false,
|
| 948 |
+
"normalized": false,
|
| 949 |
+
"special": true
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"id": 114758,
|
| 953 |
+
"content": "<|duplex_start|>",
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"lstrip": false,
|
| 956 |
+
"rstrip": false,
|
| 957 |
+
"normalized": false,
|
| 958 |
+
"special": true
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"id": 114759,
|
| 962 |
+
"content": "<|duplex_end|>",
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"lstrip": false,
|
| 965 |
+
"rstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"special": true
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"id": 114760,
|
| 971 |
+
"content": "<|system_channel|>",
|
| 972 |
+
"single_word": false,
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"rstrip": false,
|
| 975 |
+
"normalized": false,
|
| 976 |
+
"special": true
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"id": 114761,
|
| 980 |
+
"content": "<|listen|>",
|
| 981 |
+
"single_word": false,
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"id": 114762,
|
| 989 |
+
"content": "<|speak|>",
|
| 990 |
+
"single_word": false,
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"special": true
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"id": 114763,
|
| 998 |
+
"content": "<|listen_speak|>",
|
| 999 |
+
"single_word": false,
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"normalized": false,
|
| 1003 |
+
"special": true
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"id": 114764,
|
| 1007 |
+
"content": "<|output_audio_start|>",
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"lstrip": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"normalized": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"id": 114765,
|
| 1016 |
+
"content": "<|output_audio_end|>",
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"lstrip": false,
|
| 1019 |
+
"rstrip": false,
|
| 1020 |
+
"normalized": false,
|
| 1021 |
+
"special": true
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"id": 114766,
|
| 1025 |
+
"content": "<|text_start|>",
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"lstrip": false,
|
| 1028 |
+
"rstrip": false,
|
| 1029 |
+
"normalized": false,
|
| 1030 |
+
"special": true
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"id": 114767,
|
| 1034 |
+
"content": "<|text_end|>",
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"lstrip": false,
|
| 1037 |
+
"rstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"special": true
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"id": 114768,
|
| 1043 |
+
"content": "<|overlap|>",
|
| 1044 |
+
"single_word": false,
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"rstrip": false,
|
| 1047 |
+
"normalized": false,
|
| 1048 |
+
"special": true
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"id": 114769,
|
| 1052 |
+
"content": "<|barge_in|>",
|
| 1053 |
+
"single_word": false,
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"id": 114770,
|
| 1061 |
+
"content": "<|interruption|>",
|
| 1062 |
+
"single_word": false,
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"special": true
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"id": 114771,
|
| 1070 |
+
"content": "<|interruption_repair|>",
|
| 1071 |
+
"single_word": false,
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"normalized": false,
|
| 1075 |
+
"special": true
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"id": 114772,
|
| 1079 |
+
"content": "<|backchannel|>",
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"lstrip": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"normalized": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"id": 114773,
|
| 1088 |
+
"content": "<|turn_yield|>",
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"lstrip": false,
|
| 1091 |
+
"rstrip": false,
|
| 1092 |
+
"normalized": false,
|
| 1093 |
+
"special": true
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"id": 114774,
|
| 1097 |
+
"content": "<|hold|>",
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"lstrip": false,
|
| 1100 |
+
"rstrip": false,
|
| 1101 |
+
"normalized": false,
|
| 1102 |
+
"special": true
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"id": 114775,
|
| 1106 |
+
"content": "<|silence|>",
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"lstrip": false,
|
| 1109 |
+
"rstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"special": true
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"id": 114776,
|
| 1115 |
+
"content": "<|non_speech|>",
|
| 1116 |
+
"single_word": false,
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"rstrip": false,
|
| 1119 |
+
"normalized": false,
|
| 1120 |
+
"special": true
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"id": 114777,
|
| 1124 |
+
"content": "<|voice_reference_start|>",
|
| 1125 |
+
"single_word": false,
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"id": 114778,
|
| 1133 |
+
"content": "<|voice_reference_end|>",
|
| 1134 |
+
"single_word": false,
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"special": true
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"id": 114779,
|
| 1142 |
+
"content": "<|voice_reference|>",
|
| 1143 |
+
"single_word": false,
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"normalized": false,
|
| 1147 |
+
"special": true
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"id": 114780,
|
| 1151 |
+
"content": "<|voice_switch|>",
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"lstrip": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"normalized": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"id": 114781,
|
| 1160 |
+
"content": "<|speaker_style|>",
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"lstrip": false,
|
| 1163 |
+
"rstrip": false,
|
| 1164 |
+
"normalized": false,
|
| 1165 |
+
"special": true
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"id": 114782,
|
| 1169 |
+
"content": "<|prosody_control|>",
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"lstrip": false,
|
| 1172 |
+
"rstrip": false,
|
| 1173 |
+
"normalized": false,
|
| 1174 |
+
"special": true
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"id": 114783,
|
| 1178 |
+
"content": "<|zh_tw|>",
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"lstrip": false,
|
| 1181 |
+
"rstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"special": true
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"id": 114784,
|
| 1187 |
+
"content": "<|zh_hant|>",
|
| 1188 |
+
"single_word": false,
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"rstrip": false,
|
| 1191 |
+
"normalized": false,
|
| 1192 |
+
"special": true
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"id": 114785,
|
| 1196 |
+
"content": "<|taigi|>",
|
| 1197 |
+
"single_word": false,
|
| 1198 |
+
"lstrip": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"id": 114786,
|
| 1205 |
+
"content": "<|hakka|>",
|
| 1206 |
+
"single_word": false,
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"rstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"special": true
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"id": 114787,
|
| 1214 |
+
"content": "<|bopomofo|>",
|
| 1215 |
+
"single_word": false,
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"normalized": false,
|
| 1219 |
+
"special": true
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"id": 114788,
|
| 1223 |
+
"content": "<|mixed_en|>",
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"lstrip": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"normalized": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"id": 114789,
|
| 1232 |
+
"content": "<|en|>",
|
| 1233 |
+
"single_word": false,
|
| 1234 |
+
"lstrip": false,
|
| 1235 |
+
"rstrip": false,
|
| 1236 |
+
"normalized": false,
|
| 1237 |
+
"special": true
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"id": 114790,
|
| 1241 |
+
"content": "<|ja|>",
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"lstrip": false,
|
| 1244 |
+
"rstrip": false,
|
| 1245 |
+
"normalized": false,
|
| 1246 |
+
"special": true
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"id": 114791,
|
| 1250 |
+
"content": "<|ko|>",
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"lstrip": false,
|
| 1253 |
+
"rstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"special": true
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"id": 114792,
|
| 1259 |
+
"content": "<|vi|>",
|
| 1260 |
+
"single_word": false,
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"rstrip": false,
|
| 1263 |
+
"normalized": false,
|
| 1264 |
+
"special": true
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"id": 114793,
|
| 1268 |
+
"content": "<|id|>",
|
| 1269 |
+
"single_word": false,
|
| 1270 |
+
"lstrip": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"id": 114794,
|
| 1277 |
+
"content": "<|th|>",
|
| 1278 |
+
"single_word": false,
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"rstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"special": true
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"id": 114795,
|
| 1286 |
+
"content": "<|asr|>",
|
| 1287 |
+
"single_word": false,
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"normalized": false,
|
| 1291 |
+
"special": true
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"id": 114796,
|
| 1295 |
+
"content": "<|tts|>",
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"lstrip": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"normalized": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"id": 114797,
|
| 1304 |
+
"content": "<|speaker_0|>",
|
| 1305 |
+
"single_word": false,
|
| 1306 |
+
"lstrip": false,
|
| 1307 |
+
"rstrip": false,
|
| 1308 |
+
"normalized": false,
|
| 1309 |
+
"special": true
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"id": 114798,
|
| 1313 |
+
"content": "<|speaker_1|>",
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"lstrip": false,
|
| 1316 |
+
"rstrip": false,
|
| 1317 |
+
"normalized": false,
|
| 1318 |
+
"special": true
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"id": 114799,
|
| 1322 |
+
"content": "<|speaker_2|>",
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"lstrip": false,
|
| 1325 |
+
"rstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"special": true
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"id": 114800,
|
| 1331 |
+
"content": "<|speaker_3|>",
|
| 1332 |
+
"single_word": false,
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"rstrip": false,
|
| 1335 |
+
"normalized": false,
|
| 1336 |
+
"special": true
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"id": 114801,
|
| 1340 |
+
"content": "<|timestamp|>",
|
| 1341 |
+
"single_word": false,
|
| 1342 |
+
"lstrip": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"id": 114802,
|
| 1349 |
+
"content": "<|noise|>",
|
| 1350 |
+
"single_word": false,
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"rstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"special": true
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"id": 114803,
|
| 1358 |
+
"content": "<|laugh|>",
|
| 1359 |
+
"single_word": false,
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"normalized": false,
|
| 1363 |
+
"special": true
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"id": 114804,
|
| 1367 |
+
"content": "<|breath|>",
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"lstrip": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"normalized": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"id": 114805,
|
| 1376 |
+
"content": "<|pause|>",
|
| 1377 |
+
"single_word": false,
|
| 1378 |
+
"lstrip": false,
|
| 1379 |
+
"rstrip": false,
|
| 1380 |
+
"normalized": false,
|
| 1381 |
+
"special": true
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"id": 114806,
|
| 1385 |
+
"content": "<|prosody|>",
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"lstrip": false,
|
| 1388 |
+
"rstrip": false,
|
| 1389 |
+
"normalized": false,
|
| 1390 |
+
"special": true
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"id": 114807,
|
| 1394 |
+
"content": "<|pron|>",
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"lstrip": false,
|
| 1397 |
+
"rstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"special": true
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"id": 114808,
|
| 1403 |
+
"content": "</|pron|>",
|
| 1404 |
+
"single_word": false,
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"rstrip": false,
|
| 1407 |
+
"normalized": false,
|
| 1408 |
+
"special": true
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"id": 114809,
|
| 1412 |
+
"content": "<|image|>",
|
| 1413 |
+
"single_word": false,
|
| 1414 |
+
"lstrip": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"id": 114810,
|
| 1421 |
+
"content": "<|ocr|>",
|
| 1422 |
+
"single_word": false,
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"rstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"special": true
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"id": 114811,
|
| 1430 |
+
"content": "<|bbox|>",
|
| 1431 |
+
"single_word": false,
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"normalized": false,
|
| 1435 |
+
"special": true
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"id": 114812,
|
| 1439 |
+
"content": "<|line|>",
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"lstrip": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"normalized": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"id": 114813,
|
| 1448 |
+
"content": "<|table|>",
|
| 1449 |
+
"single_word": false,
|
| 1450 |
+
"lstrip": false,
|
| 1451 |
+
"rstrip": false,
|
| 1452 |
+
"normalized": false,
|
| 1453 |
+
"special": true
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"id": 114814,
|
| 1457 |
+
"content": "<|row|>",
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"lstrip": false,
|
| 1460 |
+
"rstrip": false,
|
| 1461 |
+
"normalized": false,
|
| 1462 |
+
"special": true
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"id": 114815,
|
| 1466 |
+
"content": "<|col|>",
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"lstrip": false,
|
| 1469 |
+
"rstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"special": true
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"id": 114816,
|
| 1475 |
+
"content": "<|cell|>",
|
| 1476 |
+
"single_word": false,
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"rstrip": false,
|
| 1479 |
+
"normalized": false,
|
| 1480 |
+
"special": true
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"id": 114817,
|
| 1484 |
+
"content": "<|reading_order|>",
|
| 1485 |
+
"single_word": false,
|
| 1486 |
+
"lstrip": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"id": 114818,
|
| 1493 |
+
"content": "<|source|>",
|
| 1494 |
+
"single_word": false,
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"rstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"special": true
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"id": 114819,
|
| 1502 |
+
"content": "<|cite|>",
|
| 1503 |
+
"single_word": false,
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"normalized": false,
|
| 1507 |
+
"special": true
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"id": 114820,
|
| 1511 |
+
"content": "<|evidence|>",
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"lstrip": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"normalized": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"id": 114821,
|
| 1520 |
+
"content": "<|quote|>",
|
| 1521 |
+
"single_word": false,
|
| 1522 |
+
"lstrip": false,
|
| 1523 |
+
"rstrip": false,
|
| 1524 |
+
"normalized": false,
|
| 1525 |
+
"special": true
|
| 1526 |
}
|
| 1527 |
],
|
| 1528 |
"normalizer": null,
|
|
|
|
| 1567 |
"model": {
|
| 1568 |
"type": "BPE",
|
| 1569 |
"dropout": null,
|
| 1570 |
+
"unk_token": null,
|
| 1571 |
+
"continuing_subword_prefix": "",
|
| 1572 |
+
"end_of_word_suffix": "",
|
| 1573 |
"fuse_unk": false,
|
| 1574 |
"byte_fallback": false,
|
| 1575 |
"ignore_merges": false,
|
tokenizer_config.json
CHANGED
|
@@ -1,8 +1,15 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
-
"bos_token": "<
|
| 4 |
-
"
|
|
|
|
|
|
|
| 5 |
"extra_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"<|system|>",
|
| 7 |
"<|user_channel|>",
|
| 8 |
"<|assistant_channel|>",
|
|
@@ -33,11 +40,147 @@
|
|
| 33 |
"<|image_start|>",
|
| 34 |
"<|image_end|>",
|
| 35 |
"<|video_start|>",
|
| 36 |
-
"<|video_end|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
],
|
|
|
|
|
|
|
|
|
|
| 38 |
"model_max_length": 131072,
|
| 39 |
"model_type": "byte_level_bpe",
|
| 40 |
-
"
|
|
|
|
|
|
|
|
|
|
| 41 |
"rich_transcription": {
|
| 42 |
"allow_non_speech_events": true,
|
| 43 |
"compact_json": true,
|
|
@@ -88,13 +231,20 @@
|
|
| 88 |
"<|video_end|>"
|
| 89 |
],
|
| 90 |
"strict_no_dense_timestamp_tokens": true,
|
| 91 |
-
"tokenizer_class": "
|
| 92 |
-
"unk_token": "<|unk|>",
|
| 93 |
-
"vocab_size": 114688,
|
| 94 |
-
"padding_side": "right",
|
| 95 |
"truncation_side": "right",
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
"extra_special_tokens": [
|
| 9 |
+
"<|bos|>",
|
| 10 |
+
"<|eos|>",
|
| 11 |
+
"<|unk|>",
|
| 12 |
+
"<|pad|>",
|
| 13 |
"<|system|>",
|
| 14 |
"<|user_channel|>",
|
| 15 |
"<|assistant_channel|>",
|
|
|
|
| 40 |
"<|image_start|>",
|
| 41 |
"<|image_end|>",
|
| 42 |
"<|video_start|>",
|
| 43 |
+
"<|video_end|>",
|
| 44 |
+
"<|user|>",
|
| 45 |
+
"<|assistant|>",
|
| 46 |
+
"<|tool_call|>",
|
| 47 |
+
"<|tool_response|>",
|
| 48 |
+
"<|endoftext|>",
|
| 49 |
+
"<think>",
|
| 50 |
+
"</think>",
|
| 51 |
+
"<|no_think|>",
|
| 52 |
+
"<|think|>",
|
| 53 |
+
"<|think_max|>",
|
| 54 |
+
"<|task:text_to_text|>",
|
| 55 |
+
"<|task:speech_to_speech|>",
|
| 56 |
+
"<|task:text_speech_to_text|>",
|
| 57 |
+
"<|task:text_speech_to_speech|>",
|
| 58 |
+
"<|task:full_duplex_speech|>",
|
| 59 |
+
"<|task:agent|>",
|
| 60 |
+
"<|task:tool_use|>",
|
| 61 |
+
"<|task:rag|>",
|
| 62 |
+
"<|task:code_execution|>",
|
| 63 |
+
"<|task:document_qa|>",
|
| 64 |
+
"<|task:data_analysis|>",
|
| 65 |
+
"<|task:workflow|>",
|
| 66 |
+
"<|reasoning_mode:none|>",
|
| 67 |
+
"<|reasoning_mode:short|>",
|
| 68 |
+
"<|reasoning_mode:deep|>",
|
| 69 |
+
"<|reasoning_mode:verify|>",
|
| 70 |
+
"<|private_reasoning_start|>",
|
| 71 |
+
"<|private_reasoning_end|>",
|
| 72 |
+
"<|reasoning_summary_start|>",
|
| 73 |
+
"<|reasoning_summary_end|>",
|
| 74 |
+
"<|plan_start|>",
|
| 75 |
+
"<|plan_end|>",
|
| 76 |
+
"<|step_start|>",
|
| 77 |
+
"<|step_end|>",
|
| 78 |
+
"<|action_start|>",
|
| 79 |
+
"<|action_end|>",
|
| 80 |
+
"<|observation_start|>",
|
| 81 |
+
"<|observation_end|>",
|
| 82 |
+
"<|reflection_start|>",
|
| 83 |
+
"<|reflection_end|>",
|
| 84 |
+
"<|verification_start|>",
|
| 85 |
+
"<|verification_end|>",
|
| 86 |
+
"<|tool_schema_start|>",
|
| 87 |
+
"<|tool_schema_end|>",
|
| 88 |
+
"<|tool_call_start|>",
|
| 89 |
+
"<|tool_call_end|>",
|
| 90 |
+
"<|tool_result_start|>",
|
| 91 |
+
"<|tool_result_end|>",
|
| 92 |
+
"<|tool_error_start|>",
|
| 93 |
+
"<|tool_error_end|>",
|
| 94 |
+
"<|retrieval_query_start|>",
|
| 95 |
+
"<|retrieval_query_end|>",
|
| 96 |
+
"<|citation_start|>",
|
| 97 |
+
"<|citation_end|>",
|
| 98 |
+
"<|memory_read_start|>",
|
| 99 |
+
"<|memory_read_end|>",
|
| 100 |
+
"<|memory_write_start|>",
|
| 101 |
+
"<|memory_write_end|>",
|
| 102 |
+
"<|final_answer_start|>",
|
| 103 |
+
"<|final_answer_end|>",
|
| 104 |
+
"<|json_start|>",
|
| 105 |
+
"<|json_end|>",
|
| 106 |
+
"<|code_start|>",
|
| 107 |
+
"<|code_end|>",
|
| 108 |
+
"<|markdown_start|>",
|
| 109 |
+
"<|markdown_end|>",
|
| 110 |
+
"<|duplex_start|>",
|
| 111 |
+
"<|duplex_end|>",
|
| 112 |
+
"<|system_channel|>",
|
| 113 |
+
"<|listen|>",
|
| 114 |
+
"<|speak|>",
|
| 115 |
+
"<|listen_speak|>",
|
| 116 |
+
"<|output_audio_start|>",
|
| 117 |
+
"<|output_audio_end|>",
|
| 118 |
+
"<|text_start|>",
|
| 119 |
+
"<|text_end|>",
|
| 120 |
+
"<|overlap|>",
|
| 121 |
+
"<|barge_in|>",
|
| 122 |
+
"<|interruption|>",
|
| 123 |
+
"<|interruption_repair|>",
|
| 124 |
+
"<|backchannel|>",
|
| 125 |
+
"<|turn_yield|>",
|
| 126 |
+
"<|hold|>",
|
| 127 |
+
"<|silence|>",
|
| 128 |
+
"<|non_speech|>",
|
| 129 |
+
"<|voice_reference_start|>",
|
| 130 |
+
"<|voice_reference_end|>",
|
| 131 |
+
"<|voice_reference|>",
|
| 132 |
+
"<|voice_switch|>",
|
| 133 |
+
"<|speaker_style|>",
|
| 134 |
+
"<|prosody_control|>",
|
| 135 |
+
"<|zh_tw|>",
|
| 136 |
+
"<|zh_hant|>",
|
| 137 |
+
"<|taigi|>",
|
| 138 |
+
"<|hakka|>",
|
| 139 |
+
"<|bopomofo|>",
|
| 140 |
+
"<|mixed_en|>",
|
| 141 |
+
"<|en|>",
|
| 142 |
+
"<|ja|>",
|
| 143 |
+
"<|ko|>",
|
| 144 |
+
"<|vi|>",
|
| 145 |
+
"<|id|>",
|
| 146 |
+
"<|th|>",
|
| 147 |
+
"<|asr|>",
|
| 148 |
+
"<|tts|>",
|
| 149 |
+
"<|speaker_0|>",
|
| 150 |
+
"<|speaker_1|>",
|
| 151 |
+
"<|speaker_2|>",
|
| 152 |
+
"<|speaker_3|>",
|
| 153 |
+
"<|timestamp|>",
|
| 154 |
+
"<|noise|>",
|
| 155 |
+
"<|laugh|>",
|
| 156 |
+
"<|breath|>",
|
| 157 |
+
"<|pause|>",
|
| 158 |
+
"<|prosody|>",
|
| 159 |
+
"<|pron|>",
|
| 160 |
+
"</|pron|>",
|
| 161 |
+
"<|image|>",
|
| 162 |
+
"<|ocr|>",
|
| 163 |
+
"<|bbox|>",
|
| 164 |
+
"<|line|>",
|
| 165 |
+
"<|table|>",
|
| 166 |
+
"<|row|>",
|
| 167 |
+
"<|col|>",
|
| 168 |
+
"<|cell|>",
|
| 169 |
+
"<|reading_order|>",
|
| 170 |
+
"<|source|>",
|
| 171 |
+
"<|cite|>",
|
| 172 |
+
"<|evidence|>",
|
| 173 |
+
"<|quote|>"
|
| 174 |
],
|
| 175 |
+
"fix_mistral_regex": true,
|
| 176 |
+
"is_local": false,
|
| 177 |
+
"local_files_only": false,
|
| 178 |
"model_max_length": 131072,
|
| 179 |
"model_type": "byte_level_bpe",
|
| 180 |
+
"no_audio_codec_tokens": true,
|
| 181 |
+
"no_dense_timestamp_tokens": true,
|
| 182 |
+
"pad_token": "<pad>",
|
| 183 |
+
"padding_side": "right",
|
| 184 |
"rich_transcription": {
|
| 185 |
"allow_non_speech_events": true,
|
| 186 |
"compact_json": true,
|
|
|
|
| 231 |
"<|video_end|>"
|
| 232 |
],
|
| 233 |
"strict_no_dense_timestamp_tokens": true,
|
| 234 |
+
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
|
|
|
| 235 |
"truncation_side": "right",
|
| 236 |
+
"unk_token": "<unk>",
|
| 237 |
+
"vocab_size": 114688,
|
| 238 |
+
"effective_vocab_size": 114822,
|
| 239 |
+
"open_formosa": {
|
| 240 |
+
"required_special_token_count": 157,
|
| 241 |
+
"required_special_tokens_present": true,
|
| 242 |
+
"required_special_tokens_single_id": true,
|
| 243 |
+
"standard_special_tokens": {
|
| 244 |
+
"unk_token": "<unk>",
|
| 245 |
+
"bos_token": "<s>",
|
| 246 |
+
"eos_token": "</s>",
|
| 247 |
+
"pad_token": "<pad>"
|
| 248 |
+
}
|
| 249 |
+
}
|
| 250 |
}
|