{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 15, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 16, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 33, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Split", "pattern": { "Regex": "[\\s\\S]" }, "behavior": "Isolated", "invert": false }, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 0 } } ], "special_tokens": { "": { "id": "", "ids": [ 15 ], "tokens": [ "" ] } } }, "decoder": { "type": "Fuse" }, "model": { "type": "WordLevel", "vocab": { "0": 0, "1": 1, "2": 2, "3": 3, "4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9, "+": 10, "-": 11, "*": 12, "\n": 13, " ": 14, "": 15, "": 16, "": 17, "⁰ ": 18, "¹ ": 19, "² ": 20, "³ ": 21, "⁴ ": 22, "⁵ ": 23, "⁶ ": 24, "₀ ": 25, "₁ ": 26, "₂ ": 27, "₃ ": 28, "₄ ": 29, "₅ ": 30, "₆ ": 31, "": 32, "": 33 }, "unk_token": "" } }