sanjudebnath's picture
initial test project
a1c81a0 verified
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 128,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 128
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<s>",
"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
},
{
"id": 4,
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 60,
"content": "<extra_id_0>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 61,
"content": "<extra_id_1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 62,
"content": "<extra_id_2>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 63,
"content": "<extra_id_3>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 64,
"content": "<extra_id_4>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 65,
"content": "<extra_id_5>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 66,
"content": "<extra_id_6>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 67,
"content": "<extra_id_7>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 68,
"content": "<extra_id_8>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 69,
"content": "<extra_id_9>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 70,
"content": "<extra_id_10>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 71,
"content": "<extra_id_11>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 72,
"content": "<extra_id_12>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 73,
"content": "<extra_id_13>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 74,
"content": "<extra_id_14>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 75,
"content": "<extra_id_15>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 76,
"content": "<extra_id_16>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 77,
"content": "<extra_id_17>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 78,
"content": "<extra_id_18>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 79,
"content": "<extra_id_19>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 80,
"content": "<extra_id_20>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 81,
"content": "<extra_id_21>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 82,
"content": "<extra_id_22>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 83,
"content": "<extra_id_23>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 84,
"content": "<extra_id_24>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 85,
"content": "<extra_id_25>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 86,
"content": "<extra_id_26>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 87,
"content": "<extra_id_27>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 88,
"content": "<extra_id_28>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 89,
"content": "<extra_id_29>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 90,
"content": "<extra_id_30>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 91,
"content": "<extra_id_31>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 92,
"content": "<extra_id_32>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 93,
"content": "<extra_id_33>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 94,
"content": "<extra_id_34>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 95,
"content": "<extra_id_35>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 96,
"content": "<extra_id_36>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 97,
"content": "<extra_id_37>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 98,
"content": "<extra_id_38>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 99,
"content": "<extra_id_39>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 100,
"content": "<extra_id_40>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 101,
"content": "<extra_id_41>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 102,
"content": "<extra_id_42>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 103,
"content": "<extra_id_43>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 104,
"content": "<extra_id_44>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 105,
"content": "<extra_id_45>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 106,
"content": "<extra_id_46>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 107,
"content": "<extra_id_47>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 108,
"content": "<extra_id_48>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 109,
"content": "<extra_id_49>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 110,
"content": "<extra_id_50>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 111,
"content": "<extra_id_51>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 112,
"content": "<extra_id_52>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 113,
"content": "<extra_id_53>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 114,
"content": "<extra_id_54>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 115,
"content": "<extra_id_55>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 116,
"content": "<extra_id_56>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 117,
"content": "<extra_id_57>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 118,
"content": "<extra_id_58>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 119,
"content": "<extra_id_59>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 120,
"content": "<extra_id_60>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 121,
"content": "<extra_id_61>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 122,
"content": "<extra_id_62>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 123,
"content": "<extra_id_63>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 124,
"content": "<extra_id_64>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 125,
"content": "<extra_id_65>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 126,
"content": "<extra_id_66>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 127,
"content": "<extra_id_67>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 128,
"content": "<extra_id_68>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 129,
"content": "<extra_id_69>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 130,
"content": "<extra_id_70>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 131,
"content": "<extra_id_71>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 132,
"content": "<extra_id_72>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 133,
"content": "<extra_id_73>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 134,
"content": "<extra_id_74>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 135,
"content": "<extra_id_75>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 136,
"content": "<extra_id_76>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 137,
"content": "<extra_id_77>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 138,
"content": "<extra_id_78>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 139,
"content": "<extra_id_79>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 140,
"content": "<extra_id_80>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 141,
"content": "<extra_id_81>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 142,
"content": "<extra_id_82>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 143,
"content": "<extra_id_83>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 144,
"content": "<extra_id_84>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 145,
"content": "<extra_id_85>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 146,
"content": "<extra_id_86>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 147,
"content": "<extra_id_87>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 148,
"content": "<extra_id_88>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 149,
"content": "<extra_id_89>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 150,
"content": "<extra_id_90>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 151,
"content": "<extra_id_91>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 152,
"content": "<extra_id_92>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 153,
"content": "<extra_id_93>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 154,
"content": "<extra_id_94>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 155,
"content": "<extra_id_95>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 156,
"content": "<extra_id_96>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 157,
"content": "<extra_id_97>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 158,
"content": "<extra_id_98>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 159,
"content": "<extra_id_99>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "NFD"
},
{
"type": "Lowercase"
},
{
"type": "StripAccents"
}
]
},
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "<s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
}
],
"special_tokens": {
"</s>": {
"id": "</s>",
"ids": [
2
],
"tokens": [
"</s>"
]
},
"<s>": {
"id": "<s>",
"ids": [
1
],
"tokens": [
"<s>"
]
}
}
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<pad>": 0,
"<s>": 1,
"</s>": 2,
"<unk>": 3,
"<mask>": 4,
"!": 5,
"\"": 6,
"(": 7,
")": 8,
"+": 9,
",": 10,
":": 11,
"a": 12,
"b": 13,
"c": 14,
"d": 15,
"e": 16,
"f": 17,
"h": 18,
"i": 19,
"l": 20,
"n": 21,
"o": 22,
"p": 23,
"r": 24,
"s": 25,
"t": 26,
"u": 27,
"w": 28,
"as": 29,
"el": 30,
"hel": 31,
"ld": 32,
"lo": 33,
"or": 34,
"wor": 35,
"ass": 36,
"hello": 37,
"world": 38,
"!\"": 39,
"(\"": 40,
"):": 41,
"ad": 42,
"cl": 43,
"de": 44,
"et": 45,
"in": 46,
"pr": 47,
"pass": 48,
"rn": 49,
"ret": 50,
"urn": 51,
"helloworld": 52,
"!\")": 53,
"add": 54,
"class": 55,
"def": 56,
"int": 57,
"print": 58,
"return": 59
},
"merges": [
[
"a",
"s"
],
[
"e",
"l"
],
[
"h",
"el"
],
[
"l",
"d"
],
[
"l",
"o"
],
[
"o",
"r"
],
[
"w",
"or"
],
[
"as",
"s"
],
[
"hel",
"lo"
],
[
"wor",
"ld"
],
[
"!",
"\""
],
[
"(",
"\""
],
[
")",
":"
],
[
"a",
"d"
],
[
"c",
"l"
],
[
"d",
"e"
],
[
"e",
"t"
],
[
"i",
"n"
],
[
"p",
"r"
],
[
"p",
"ass"
],
[
"r",
"n"
],
[
"r",
"et"
],
[
"u",
"rn"
],
[
"hello",
"world"
],
[
"!\"",
")"
],
[
"ad",
"d"
],
[
"cl",
"ass"
],
[
"de",
"f"
],
[
"in",
"t"
],
[
"pr",
"int"
],
[
"ret",
"urn"
]
]
}
}