{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[EOS]", "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": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": { "type": "TemplateProcessing", "single": [ { "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": { "[EOS]": { "id": "[EOS]", "ids": [ 0 ], "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, "vocab": { "[EOS]": 0, "[UNK]": 1, "[CLS]": 2, "[PAD]": 3, "+": 4, "-": 5, "0": 6, "1": 7, "2": 8, "3": 9, "4": 10, "5": 11, "6": 12, "7": 13, "8": 14, "9": 15, "=": 16, "10": 17, "99": 18, "98": 19, "11": 20, "12": 21, "97": 22, "13": 23, "96": 24, "95": 25, "14": 26, "15": 27, "94": 28, "93": 29, "16": 30, "92": 31, "17": 32, "18": 33, "91": 34, "19": 35, "90": 36, "89": 37, "20": 38, "21": 39, "88": 40, "22": 41, "87": 42, "23": 43, "86": 44, "85": 45, "24": 46, "25": 47, "84": 48, "26": 49, "83": 50, "27": 51, "82": 52 }, "merges": [ "1 0", "9 9", "9 8", "1 1", "1 2", "9 7", "1 3", "9 6", "9 5", "1 4", "1 5", "9 4", "9 3", "1 6", "9 2", "1 7", "1 8", "9 1", "1 9", "9 0", "8 9", "2 0", "2 1", "8 8", "2 2", "8 7", "2 3", "8 6", "8 5", "2 4", "2 5", "8 4", "2 6", "8 3", "2 7", "8 2" ] } }