| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "<s>", | |
| "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": "</s>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 4, | |
| "content": "[MASK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 5, | |
| "content": "[SEP]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 6, | |
| "content": "[CLS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Sequence", | |
| "normalizers": [ | |
| { | |
| "type": "Strip", | |
| "strip_left": false, | |
| "strip_right": true | |
| }, | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "String": " {2,}" | |
| }, | |
| "content": "▁" | |
| } | |
| ] | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Sequence", | |
| "pretokenizers": [ | |
| { | |
| "type": "WhitespaceSplit" | |
| }, | |
| { | |
| "type": "Metaspace", | |
| "replacement": "▁", | |
| "prepend_scheme": "always", | |
| "split": true | |
| } | |
| ] | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "<s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "SpecialToken": { | |
| "id": "<s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "</s>": { | |
| "id": "</s>", | |
| "ids": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "</s>" | |
| ] | |
| }, | |
| "<s>": { | |
| "id": "<s>", | |
| "ids": [ | |
| 0 | |
| ], | |
| "tokens": [ | |
| "<s>" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": { | |
| "type": "Metaspace", | |
| "replacement": "▁", | |
| "prepend_scheme": "always", | |
| "split": true | |
| }, | |
| "model": { | |
| "type": "Unigram", | |
| "unk_id": 3, | |
| "vocab": [ | |
| [ | |
| "<s>", | |
| 0.0 | |
| ], | |
| [ | |
| "[PAD]", | |
| 0.0 | |
| ], | |
| [ | |
| "</s>", | |
| 0.0 | |
| ], | |
| [ | |
| "[UNK]", | |
| 0.0 | |
| ], | |
| [ | |
| "[MASK]", | |
| 0.0 | |
| ] | |
| ], | |
| "byte_fallback": false | |
| } | |
| } |