{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "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": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 3 ], "tokens": [ "" ] }, "": { "id": "", "ids": [ 4 ], "tokens": [ "" ] } } }, "decoder": null, "model": { "type": "WordPiece", "unk_token": "", "continuing_subword_prefix": "##", "max_input_chars_per_word": 100, "vocab": { "": 0, "": 1, "": 2, "": 3, "": 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 } } }