GPT2_EN_200 / tokenizer.json
xiulinyang's picture
Add checkpoint
427128c
{
"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": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Lowercase"
},
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<|endoftext|>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<|endoftext|>": {
"id": "<|endoftext|>",
"ids": [
1
],
"tokens": [
"<|endoftext|>"
]
}
}
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<unk>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<pad>": 0,
"<|endoftext|>": 1,
"<s>": 2,
"<unk>": 3,
"!": 4,
"\"": 5,
"#": 6,
"$": 7,
"%": 8,
"&": 9,
"'": 10,
"(": 11,
")": 12,
"*": 13,
"+": 14,
",": 15,
"-": 16,
".": 17,
"/": 18,
"0": 19,
"1": 20,
"2": 21,
"3": 22,
"4": 23,
"5": 24,
"6": 25,
"7": 26,
"8": 27,
"9": 28,
":": 29,
";": 30,
"<": 31,
"=": 32,
">": 33,
"?": 34,
"@": 35,
"[": 36,
"\\": 37,
"]": 38,
"^": 39,
"_": 40,
"`": 41,
"a": 42,
"b": 43,
"c": 44,
"d": 45,
"e": 46,
"f": 47,
"g": 48,
"h": 49,
"i": 50,
"j": 51,
"k": 52,
"l": 53,
"m": 54,
"n": 55,
"o": 56,
"p": 57,
"q": 58,
"r": 59,
"s": 60,
"t": 61,
"u": 62,
"v": 63,
"w": 64,
"x": 65,
"y": 66,
"z": 67,
"{": 68,
"|": 69,
"}": 70,
"~": 71,
"¡": 72,
"¢": 73,
"£": 74,
"¤": 75,
"¥": 76,
"¦": 77,
"§": 78,
"¨": 79,
"©": 80,
"ª": 81,
"«": 82,
"¬": 83,
"®": 84,
"¯": 85,
"°": 86,
"±": 87,
"²": 88,
"³": 89,
"´": 90,
"µ": 91,
"¶": 92,
"·": 93,
"¸": 94,
"¹": 95,
"º": 96,
"»": 97,
"¼": 98,
"½": 99,
"¾": 100,
"¿": 101,
"Â": 102,
"Ã": 103,
"Ä": 104,
"Å": 105,
"Æ": 106,
"Ç": 107,
"È": 108,
"É": 109,
"Ê": 110,
"Ì": 111,
"Î": 112,
"Ï": 113,
"Ð": 114,
"Ñ": 115,
"Ò": 116,
"Ó": 117,
"Ö": 118,
"×": 119,
"Ø": 120,
"Ù": 121,
"Ú": 122,
"Û": 123,
"Þ": 124,
"à": 125,
"á": 126,
"â": 127,
"ã": 128,
"ä": 129,
"å": 130,
"æ": 131,
"ç": 132,
"è": 133,
"é": 134,
"ê": 135,
"ë": 136,
"ì": 137,
"í": 138,
"î": 139,
"ï": 140,
"ð": 141,
"Ċ": 142,
"Ġ": 143,
"Ģ": 144,
"ģ": 145,
"Ĥ": 146,
"ĥ": 147,
"Ħ": 148,
"ħ": 149,
"Ĩ": 150,
"ĩ": 151,
"Ī": 152,
"ī": 153,
"Ĭ": 154,
"ĭ": 155,
"Į": 156,
"į": 157,
"İ": 158,
"ı": 159,
"IJ": 160,
"ij": 161,
"Ĵ": 162,
"ĵ": 163,
"Ķ": 164,
"ķ": 165,
"ĸ": 166,
"Ĺ": 167,
"ĺ": 168,
"Ļ": 169,
"ļ": 170,
"Ľ": 171,
"ľ": 172,
"Ŀ": 173,
"ŀ": 174,
"Ł": 175,
"ł": 176,
"Ń": 177,
"Ġt": 178,
"Ġa": 179,
"Ġth": 180,
"Ġi": 181,
"Ġw": 182,
"ou": 183,
"Ġs": 184,
"er": 185,
"Ġthe": 186,
"in": 187,
"Ġh": 188,
"Ġo": 189,
"re": 190,
"at": 191,
"Ġy": 192,
"Ġm": 193,
"Ġc": 194,
"Ġb": 195,
"nd": 196,
"Ġyou": 197,
"Ġd": 198,
"Ġf": 199
},
"merges": [
[
"Ġ",
"t"
],
[
"Ġ",
"a"
],
[
"Ġt",
"h"
],
[
"Ġ",
"i"
],
[
"Ġ",
"w"
],
[
"o",
"u"
],
[
"Ġ",
"s"
],
[
"e",
"r"
],
[
"Ġth",
"e"
],
[
"i",
"n"
],
[
"Ġ",
"h"
],
[
"Ġ",
"o"
],
[
"r",
"e"
],
[
"a",
"t"
],
[
"Ġ",
"y"
],
[
"Ġ",
"m"
],
[
"Ġ",
"c"
],
[
"Ġ",
"b"
],
[
"n",
"d"
],
[
"Ġy",
"ou"
],
[
"Ġ",
"d"
],
[
"Ġ",
"f"
]
]
}
}