{ "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 } ], "normalizer": { "type": "Sequence", "normalizers": [] }, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true }, "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": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 2 ], "tokens": [ "" ] }, "": { "id": "", "ids": [ 3 ], "tokens": [ "" ] } } }, "decoder": { "type": "ByteLevel", "add_prefix_space": false, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": true, "vocab": { "<0x00>": 0, "<0x01>": 1, "<0x02>": 2, "<0x03>": 3, "<0x04>": 4, "<0x05>": 5, "<0x06>": 6, "<0x07>": 7, "<0x08>": 8, "<0x09>": 9, "<0x0A>": 10, "<0x0B>": 11, "<0x0C>": 12, "<0x0D>": 13, "<0x0E>": 14, "<0x0F>": 15, "<0x10>": 16, "<0x11>": 17, "<0x12>": 18, "<0x13>": 19, "<0x14>": 20, "<0x15>": 21, "<0x16>": 22, "<0x17>": 23, "<0x18>": 24, "<0x19>": 25, "<0x1A>": 26, "<0x1B>": 27, "<0x1C>": 28, "<0x1D>": 29, "<0x1E>": 30, "<0x1F>": 31, " ": 32, "!": 33, "\"": 34, "#": 35, "$": 36, "%": 37, "&": 38, "'": 39, "(": 40, ")": 41, "*": 42, "+": 43, ",": 44, "-": 45, ".": 46, "/": 47, "0": 48, "1": 49, "2": 50, "3": 51, "4": 52, "5": 53, "6": 54, "7": 55, "8": 56, "9": 57, ":": 58, ";": 59, "<": 60, "=": 61, ">": 62, "?": 63, "@": 64, "A": 65, "B": 66, "C": 67, "D": 68, "E": 69, "F": 70, "G": 71, "H": 72, "I": 73, "J": 74, "K": 75, "L": 76, "M": 77, "N": 78, "O": 79, "P": 80, "Q": 81, "R": 82, "S": 83, "T": 84, "U": 85, "V": 86, "W": 87, "X": 88, "Y": 89, "Z": 90, "[": 91, "\\": 92, "]": 93, "^": 94, "_": 95, "`": 96, "a": 97, "b": 98, "c": 99, "d": 100, "e": 101, "f": 102, "g": 103, "h": 104, "i": 105, "j": 106, "k": 107, "l": 108, "m": 109, "n": 110, "o": 111, "p": 112, "q": 113, "r": 114, "s": 115, "t": 116, "u": 117, "v": 118, "w": 119, "x": 120, "y": 121, "z": 122, "{": 123, "|": 124, "}": 125, "~": 126, "<0x7F>": 127, "<0x80>": 128, "<0x81>": 129, "<0x82>": 130, "<0x83>": 131, "<0x84>": 132, "<0x85>": 133, "<0x86>": 134, "<0x87>": 135, "<0x88>": 136, "<0x89>": 137, "<0x8A>": 138, "<0x8B>": 139, "<0x8C>": 140, "<0x8D>": 141, "<0x8E>": 142, "<0x8F>": 143, "<0x90>": 144, "<0x91>": 145, "<0x92>": 146, "<0x93>": 147, "<0x94>": 148, "<0x95>": 149, "<0x96>": 150, "<0x97>": 151, "<0x98>": 152, "<0x99>": 153, "<0x9A>": 154, "<0x9B>": 155, "<0x9C>": 156, "<0x9D>": 157, "<0x9E>": 158, "<0x9F>": 159, "<0xA0>": 160, "<0xA1>": 161, "<0xA2>": 162, "<0xA3>": 163, "<0xA4>": 164, "<0xA5>": 165, "<0xA6>": 166, "<0xA7>": 167, "<0xA8>": 168, "<0xA9>": 169, "<0xAA>": 170, "<0xAB>": 171, "<0xAC>": 172, "<0xAD>": 173, "<0xAE>": 174, "<0xAF>": 175, "<0xB0>": 176, "<0xB1>": 177, "<0xB2>": 178, "<0xB3>": 179, "<0xB4>": 180, "<0xB5>": 181, "<0xB6>": 182, "<0xB7>": 183, "<0xB8>": 184, "<0xB9>": 185, "<0xBA>": 186, "<0xBB>": 187, "<0xBC>": 188, "<0xBD>": 189, "<0xBE>": 190, "<0xBF>": 191, "<0xC0>": 192, "<0xC1>": 193, "<0xC2>": 194, "<0xC3>": 195, "<0xC4>": 196, "<0xC5>": 197, "<0xC6>": 198, "<0xC7>": 199, "<0xC8>": 200, "<0xC9>": 201, "<0xCA>": 202, "<0xCB>": 203, "<0xCC>": 204, "<0xCD>": 205, "<0xCE>": 206, "<0xCF>": 207, "<0xD0>": 208, "<0xD1>": 209, "<0xD2>": 210, "<0xD3>": 211, "<0xD4>": 212, "<0xD5>": 213, "<0xD6>": 214, "<0xD7>": 215, "<0xD8>": 216, "<0xD9>": 217, "<0xDA>": 218, "<0xDB>": 219, "<0xDC>": 220, "<0xDD>": 221, "<0xDE>": 222, "<0xDF>": 223, "<0xE0>": 224, "<0xE1>": 225, "<0xE2>": 226, "<0xE3>": 227, "<0xE4>": 228, "<0xE5>": 229, "<0xE6>": 230, "<0xE7>": 231, "<0xE8>": 232, "<0xE9>": 233, "<0xEA>": 234, "<0xEB>": 235, "<0xEC>": 236, "<0xED>": 237, "<0xEE>": 238, "<0xEF>": 239, "<0xF0>": 240, "<0xF1>": 241, "<0xF2>": 242, "<0xF3>": 243, "<0xF4>": 244, "<0xF5>": 245, "<0xF6>": 246, "<0xF7>": 247, "<0xF8>": 248, "<0xF9>": 249, "<0xFA>": 250, "<0xFB>": 251, "<0xFC>": 252, "<0xFD>": 253, "<0xFE>": 254, "<0xFF>": 255, "": 0, "": 1, "": 2, "": 3, "": 4 }, "merges": [] } }