| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "UNK", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "PAD", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "WORD_BOUNDARY", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "UTT_BOUNDARY", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Sequence", | |
| "normalizers": [ | |
| { | |
| "type": "Strip", | |
| "strip_left": true, | |
| "strip_right": true | |
| } | |
| ] | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "UTT_BOUNDARY", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "SpecialToken": { | |
| "id": "UTT_BOUNDARY", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "UTT_BOUNDARY", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "UTT_BOUNDARY": { | |
| "id": "UTT_BOUNDARY", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "UTT_BOUNDARY" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "UNK": 0, | |
| "PAD": 1, | |
| "WORD_BOUNDARY": 2, | |
| "UTT_BOUNDARY": 3, | |
| "蓻": 4, | |
| "l": 5, | |
| "尾": 6, | |
| "瑟": 7, | |
| "n": 8, | |
| "a": 9, | |
| "s": 10, | |
| "t": 11, | |
| "r": 12, | |
| "d": 13, | |
| "a藧": 14, | |
| "t虪蕛": 15, | |
| "m": 16, | |
| "蓴": 17, | |
| "h": 18, | |
| "p": 19, | |
| "蕣": 20, | |
| "伞": 21, | |
| "k": 22, | |
| "q": 23, | |
| "f": 24, | |
| "j": 25, | |
| "w": 26, | |
| "蕩": 27, | |
| "p始": 28, | |
| "蕯": 29, | |
| "t始": 30, | |
| "t虪蕛始": 31, | |
| "k始": 32, | |
| "瑟藧": 33, | |
| "q始": 34, | |
| "蓻藧": 35 | |
| }, | |
| "unk_token": "UNK" | |
| } | |
| } |