{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [], "normalizer": null, "pre_tokenizer": { "type": "BertPreTokenizer" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "Sequence": { "id": "A", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 0 ], "tokens": [ "" ] } } }, "decoder": { "type": "WordPiece", "prefix": "", "cleanup": true }, "model": { "type": "WordPiece", "unk_token": "", "continuing_subword_prefix": "", "max_input_chars_per_word": 10000000000, "vocab": { "": 0, "": 1, "": 2, "": 3, "L": 4, "A": 5, "G": 6, "V": 7, "S": 8, "E": 9, "R": 10, "T": 11, "I": 12, "D": 13, "P": 14, "K": 15, "Q": 16, "N": 17, "F": 18, "Y": 19, "M": 20, "H": 21, "W": 22, "C": 23, "X": 24, "B": 25, "U": 26, "Z": 27, "O": 28, ".": 29, "-": 30, "": 31, "": 32 } } }