{ "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": "[BOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "Lowercase" }, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": ".{1}" }, "behavior": "Isolated", "invert": false }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "[BOS]", "type_id": 0 } }, { "Sequence": { "id": "A", "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]" ] } } }, "decoder": { "type": "Fuse" }, "model": { "type": "WordLevel", "vocab": { "[PAD]": 0, "[UNK]": 1, "[BOS]": 2, "a": 3, "c": 4, "g": 5, "t": 6 }, "unk_token": "[UNK]" } }