| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[EOS]", | |
| "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": "[CLS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[PAD]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "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": { | |
| "[EOS]": { | |
| "id": "[EOS]", | |
| "ids": [ | |
| 0 | |
| ], | |
| "tokens": [ | |
| "[EOS]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": "[UNK]", | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": false, | |
| "byte_fallback": false, | |
| "vocab": { | |
| "[EOS]": 0, | |
| "[UNK]": 1, | |
| "[CLS]": 2, | |
| "[PAD]": 3, | |
| "+": 4, | |
| "-": 5, | |
| "0": 6, | |
| "1": 7, | |
| "2": 8, | |
| "3": 9, | |
| "4": 10, | |
| "5": 11, | |
| "6": 12, | |
| "7": 13, | |
| "8": 14, | |
| "9": 15, | |
| "99": 16, | |
| "10": 17, | |
| "11": 18, | |
| "98": 19, | |
| "97": 20, | |
| "12": 21, | |
| "96": 22, | |
| "13": 23, | |
| "14": 24, | |
| "95": 25, | |
| "15": 26, | |
| "94": 27, | |
| "16": 28, | |
| "93": 29, | |
| "92": 30, | |
| "17": 31, | |
| "18": 32, | |
| "91": 33, | |
| "19": 34, | |
| "90": 35, | |
| "89": 36, | |
| "20": 37, | |
| "21": 38, | |
| "88": 39, | |
| "22": 40, | |
| "87": 41, | |
| "86": 42, | |
| "23": 43, | |
| "24": 44, | |
| "85": 45, | |
| "25": 46, | |
| "84": 47, | |
| "26": 48, | |
| "83": 49, | |
| "27": 50, | |
| "82": 51 | |
| }, | |
| "merges": [ | |
| "9 9", | |
| "1 0", | |
| "1 1", | |
| "9 8", | |
| "9 7", | |
| "1 2", | |
| "9 6", | |
| "1 3", | |
| "1 4", | |
| "9 5", | |
| "1 5", | |
| "9 4", | |
| "1 6", | |
| "9 3", | |
| "9 2", | |
| "1 7", | |
| "1 8", | |
| "9 1", | |
| "1 9", | |
| "9 0", | |
| "8 9", | |
| "2 0", | |
| "2 1", | |
| "8 8", | |
| "2 2", | |
| "8 7", | |
| "8 6", | |
| "2 3", | |
| "2 4", | |
| "8 5", | |
| "2 5", | |
| "8 4", | |
| "2 6", | |
| "8 3", | |
| "2 7", | |
| "8 2" | |
| ] | |
| } | |
| } |