| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 0, |
| "content": "<pad>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 1, |
| "content": "<unk>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 2, |
| "content": "<mask>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 3, |
| "content": "<bos>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 4, |
| "content": "<eos>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| }, |
| { |
| "id": 5, |
| "content": "|", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": null, |
| "pre_tokenizer": { |
| "type": "Split", |
| "pattern": { |
| "String": "" |
| }, |
| "behavior": "Removed", |
| "invert": false |
| }, |
| "post_processor": { |
| "type": "TemplateProcessing", |
| "single": [ |
| { |
| "SpecialToken": { |
| "id": "<bos>", |
| "type_id": 0 |
| } |
| }, |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| }, |
| { |
| "SpecialToken": { |
| "id": "<eos>", |
| "type_id": 0 |
| } |
| } |
| ], |
| "pair": [ |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| }, |
| { |
| "Sequence": { |
| "id": "B", |
| "type_id": 1 |
| } |
| } |
| ], |
| "special_tokens": { |
| "<bos>": { |
| "id": "<bos>", |
| "ids": [ |
| 3 |
| ], |
| "tokens": [ |
| "<bos>" |
| ] |
| }, |
| "<eos>": { |
| "id": "<eos>", |
| "ids": [ |
| 4 |
| ], |
| "tokens": [ |
| "<eos>" |
| ] |
| } |
| } |
| }, |
| "decoder": null, |
| "model": { |
| "type": "WordPiece", |
| "unk_token": "<unk>", |
| "continuing_subword_prefix": "##", |
| "max_input_chars_per_word": 100, |
| "vocab": { |
| "<pad>": 0, |
| "<unk>": 1, |
| "<mask>": 2, |
| "<bos>": 3, |
| "<eos>": 4, |
| "|": 5, |
| "L": 6, |
| "A": 7, |
| "G": 8, |
| "V": 9, |
| "S": 10, |
| "E": 11, |
| "R": 12, |
| "T": 13, |
| "I": 14, |
| "D": 15, |
| "P": 16, |
| "K": 17, |
| "Q": 18, |
| "N": 19, |
| "F": 20, |
| "Y": 21, |
| "M": 22, |
| "H": 23, |
| "W": 24, |
| "C": 25, |
| "B": 26 |
| } |
| } |
| } |
