| { | |
| "version": "1.0", | |
| "truncation": { | |
| "direction": "Right", | |
| "max_length": 128, | |
| "strategy": "LongestFirst", | |
| "stride": 0 | |
| }, | |
| "padding": { | |
| "strategy": { | |
| "Fixed": 128 | |
| }, | |
| "direction": "Right", | |
| "pad_to_multiple_of": null, | |
| "pad_id": 0, | |
| "pad_type_id": 0, | |
| "pad_token": "[PAD]" | |
| }, | |
| "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": "[BOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[EOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Split", | |
| "pattern": { | |
| "String": "" | |
| }, | |
| "behavior": "Isolated", | |
| "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": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "[BOS]" | |
| ] | |
| }, | |
| "[EOS]": { | |
| "id": "[EOS]", | |
| "ids": [ | |
| 3 | |
| ], | |
| "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, | |
| "ignore_merges": false, | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[UNK]": 1, | |
| "[BOS]": 2, | |
| "[EOS]": 3, | |
| "\u0001": 4, | |
| "#": 5, | |
| "(": 6, | |
| ")": 7, | |
| "+": 8, | |
| "-": 9, | |
| "/": 10, | |
| "1": 11, | |
| "2": 12, | |
| "3": 13, | |
| "4": 14, | |
| "5": 15, | |
| "6": 16, | |
| "7": 17, | |
| "8": 18, | |
| "=": 19, | |
| "@": 20, | |
| "B": 21, | |
| "C": 22, | |
| "F": 23, | |
| "H": 24, | |
| "I": 25, | |
| "N": 26, | |
| "O": 27, | |
| "P": 28, | |
| "S": 29, | |
| "[": 30, | |
| "\\": 31, | |
| "]": 32, | |
| "c": 33, | |
| "e": 34, | |
| "i": 35, | |
| "l": 36, | |
| "n": 37, | |
| "o": 38, | |
| "p": 39, | |
| "r": 40, | |
| "s": 41 | |
| }, | |
| "merges": [] | |
| } | |
| } |