gpt2-2layer-1m / tokenizer.json
gvadhul's picture
Upload folder using huggingface_hub
dad87ca verified
Raw
History Blame Contribute Delete
9.42 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|endoftext|>",
"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
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
},
"post_processor": null,
"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": {
"<|endoftext|>": 0,
"<|unk|>": 1,
"!": 2,
".": 3,
"H": 4,
"I": 5,
"O": 6,
"T": 7,
"a": 8,
"b": 9,
"c": 10,
"d": 11,
"e": 12,
"f": 13,
"g": 14,
"h": 15,
"i": 16,
"j": 17,
"k": 18,
"l": 19,
"m": 20,
"n": 21,
"o": 22,
"p": 23,
"q": 24,
"r": 25,
"s": 26,
"t": 27,
"u": 28,
"v": 29,
"w": 30,
"x": 31,
"y": 32,
"z": 33,
"Ċ": 34,
"Ġ": 35,
"Ġt": 36,
"Ġa": 37,
"el": 38,
"er": 39,
"Th": 40,
"del": 41,
"es": 42,
"fo": 43,
"in": 44,
"is": 45,
"la": 46,
"mo": 47,
"Ġla": 48,
"Ġmo": 49,
"Ġtes": 50,
"Ġmodel": 51,
"Ġtest": 52,
"al": 53,
"as": 54,
"ed": 55,
"on": 56,
"ra": 57,
"wo": 58,
"Ġb": 59,
"Ġo": 60,
"Ġu": 61,
"Ġfo": 62,
"Ġis": 63,
"Ġth": 64,
"Ġtin": 65,
"The": 66,
"Ġtiny": 67,
"Hel": 68,
"In": 69,
"On": 70,
"ag": 71,
"ce": 72,
"ck": 73,
"do": 74,
"eg": 75,
"eed": 76,
"gu": 77,
"has": 78,
"id": 79,
"im": 80,
"ion": 81,
"ick": 82,
"ju": 83,
"ld": 84,
"lo": 85,
"mp": 86,
"mer": 87,
"mal": 88,
"nd": 89,
"ns": 90,
"need": 91,
"ngu": 92,
"ow": 93,
"pon": 94,
"qu": 95,
"rld": 96,
"rmer": 97,
"row": 98,
"sed": 99,
"smal": 100,
"teg": 101,
"tion": 102,
"ut": 103,
"ver": 104,
"val": 105,
"was": 106,
"yer": 107,
"zy": 108,
"ĠTh": 109,
"Ġwo": 110,
"Ġdo": 111,
"Ġhas": 112,
"Ġju": 113,
"Ġneed": 114,
"Ġqu": 115,
"Ġsmal": 116,
"Ġval": 117,
"Ġwas": 118,
"Ġtra": 119,
"Ġtwo": 120,
"Ġtim": 121,
"Ġand": 122,
"ere": 123,
"former": 124,
"ing": 125,
"Ġlangu": 126,
"Ġlayer": 127,
"Ġlazy": 128,
"Ġtests": 129,
"Ġtesting": 130,
"ration": 131,
"Ġbrow": 132,
"Ġbut": 133,
"Ġof": 134,
"Ġover": 135,
"Ġupon": 136,
"Ġused": 137,
"Ġfor": 138,
"Ġfox": 139,
"Ġthe": 140,
"Ġthere": 141,
"Hello": 142,
"Integ": 143,
"Once": 144,
"age": 145,
"mps": 146,
"nsformer": 147,
"ĠThis": 148,
"Ġworld": 149,
"Ġdog": 150,
"Ġjumps": 151,
"Ġquick": 152,
"Ġsmall": 153,
"Ġvalid": 154,
"Ġtransformer": 155,
"Ġtime": 156,
"Ġlanguage": 157,
"Ġlayers": 158,
"Ġbrown": 159,
"Integration": 160
},
"merges": [
[
"Ġ",
"t"
],
[
"Ġ",
"a"
],
[
"e",
"l"
],
[
"e",
"r"
],
[
"T",
"h"
],
[
"d",
"el"
],
[
"e",
"s"
],
[
"f",
"o"
],
[
"i",
"n"
],
[
"i",
"s"
],
[
"l",
"a"
],
[
"m",
"o"
],
[
"Ġ",
"la"
],
[
"Ġ",
"mo"
],
[
"Ġt",
"es"
],
[
"Ġmo",
"del"
],
[
"Ġtes",
"t"
],
[
"a",
"l"
],
[
"a",
"s"
],
[
"e",
"d"
],
[
"o",
"n"
],
[
"r",
"a"
],
[
"w",
"o"
],
[
"Ġ",
"b"
],
[
"Ġ",
"o"
],
[
"Ġ",
"u"
],
[
"Ġ",
"fo"
],
[
"Ġ",
"is"
],
[
"Ġt",
"h"
],
[
"Ġt",
"in"
],
[
"Th",
"e"
],
[
"Ġtin",
"y"
],
[
"H",
"el"
],
[
"I",
"n"
],
[
"O",
"n"
],
[
"a",
"g"
],
[
"c",
"e"
],
[
"c",
"k"
],
[
"d",
"o"
],
[
"e",
"g"
],
[
"e",
"ed"
],
[
"g",
"u"
],
[
"h",
"as"
],
[
"i",
"d"
],
[
"i",
"m"
],
[
"i",
"on"
],
[
"i",
"ck"
],
[
"j",
"u"
],
[
"l",
"d"
],
[
"l",
"o"
],
[
"m",
"p"
],
[
"m",
"er"
],
[
"m",
"al"
],
[
"n",
"d"
],
[
"n",
"s"
],
[
"n",
"eed"
],
[
"n",
"gu"
],
[
"o",
"w"
],
[
"p",
"on"
],
[
"q",
"u"
],
[
"r",
"ld"
],
[
"r",
"mer"
],
[
"r",
"ow"
],
[
"s",
"ed"
],
[
"s",
"mal"
],
[
"t",
"eg"
],
[
"t",
"ion"
],
[
"u",
"t"
],
[
"v",
"er"
],
[
"v",
"al"
],
[
"w",
"as"
],
[
"y",
"er"
],
[
"z",
"y"
],
[
"Ġ",
"Th"
],
[
"Ġ",
"wo"
],
[
"Ġ",
"do"
],
[
"Ġ",
"has"
],
[
"Ġ",
"ju"
],
[
"Ġ",
"need"
],
[
"Ġ",
"qu"
],
[
"Ġ",
"smal"
],
[
"Ġ",
"val"
],
[
"Ġ",
"was"
],
[
"Ġt",
"ra"
],
[
"Ġt",
"wo"
],
[
"Ġt",
"im"
],
[
"Ġa",
"nd"
],
[
"er",
"e"
],
[
"fo",
"rmer"
],
[
"in",
"g"
],
[
"Ġla",
"ngu"
],
[
"Ġla",
"yer"
],
[
"Ġla",
"zy"
],
[
"Ġtest",
"s"
],
[
"Ġtest",
"ing"
],
[
"ra",
"tion"
],
[
"Ġb",
"row"
],
[
"Ġb",
"ut"
],
[
"Ġo",
"f"
],
[
"Ġo",
"ver"
],
[
"Ġu",
"pon"
],
[
"Ġu",
"sed"
],
[
"Ġfo",
"r"
],
[
"Ġfo",
"x"
],
[
"Ġth",
"e"
],
[
"Ġth",
"ere"
],
[
"Hel",
"lo"
],
[
"In",
"teg"
],
[
"On",
"ce"
],
[
"ag",
"e"
],
[
"mp",
"s"
],
[
"ns",
"former"
],
[
"ĠTh",
"is"
],
[
"Ġwo",
"rld"
],
[
"Ġdo",
"g"
],
[
"Ġju",
"mps"
],
[
"Ġqu",
"ick"
],
[
"Ġsmal",
"l"
],
[
"Ġval",
"id"
],
[
"Ġtra",
"nsformer"
],
[
"Ġtim",
"e"
],
[
"Ġlangu",
"age"
],
[
"Ġlayer",
"s"
],
[
"Ġbrow",
"n"
],
[
"Integ",
"ration"
]
]
}
}