roberta-base-emphasis / tokenizer.json
Davidsamuel101's picture
Upload tokenizer
677d0c8 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 86,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 87,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 88,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 89,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 90,
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
}
]
},
"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
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 1
}
}
],
"special_tokens": {
"</s>": {
"id": "</s>",
"ids": [
89
],
"tokens": [
"</s>"
]
},
"<s>": {
"id": "<s>",
"ids": [
88
],
"tokens": [
"<s>"
]
}
}
},
"decoder": {
"type": "WordPiece",
"prefix": "",
"cleanup": true
},
"model": {
"type": "WordLevel",
"vocab": {
"aɪ": 0,
"aʊ": 1,
"b": 2,
"d": 3,
"d͡ʒ": 4,
"eɪ": 5,
"f": 6,
"h": 7,
"i": 8,
"j": 9,
"k": 10,
"l": 11,
"m": 12,
"n": 13,
"oʊ": 14,
"p": 15,
"s": 16,
"t": 17,
"t͡ʃ": 18,
"u": 19,
"v": 20,
"w": 21,
"z": 22,
"æ": 23,
"ð": 24,
"ŋ": 25,
"ɑ": 26,
"ɔ": 27,
"ɔɪ": 28,
"ə": 29,
"ɚ": 30,
"ɛ": 31,
"ɡ": 32,
"ɪ": 33,
"ɹ": 34,
"ʃ": 35,
"ʊ": 36,
"ʌ": 37,
"ʒ": 38,
"ˈaɪ": 39,
"ˈaʊ": 40,
"ˈeɪ": 41,
"ˈi": 42,
"ˈoʊ": 43,
"ˈu": 44,
"ˈæ": 45,
"ˈɑ": 46,
"ˈɔ": 47,
"ˈɔɪ": 48,
"ˈɚ": 49,
"ˈɛ": 50,
"ˈɪ": 51,
"ˈʊ": 52,
"ˈʌ": 53,
"ˌaɪ": 54,
"ˌaʊ": 55,
"ˌeɪ": 56,
"ˌi": 57,
"ˌoʊ": 58,
"ˌu": 59,
"ˌæ": 60,
"ˌɑ": 61,
"ˌɔ": 62,
"ˌɔɪ": 63,
"ˌɚ": 64,
"ˌɛ": 65,
"ˌɪ": 66,
"ˌʊ": 67,
"ˌʌ": 68,
"θ": 69,
"\"": 70,
" ": 71,
"_": 72,
"^": 73,
"$": 74,
"!": 75,
"#": 76,
"'": 77,
"(": 78,
")": 79,
",": 80,
"-": 81,
".": 82,
":": 83,
";": 84,
"?": 85,
"<unk>": 86,
"<pad>": 87,
"<s>": 88,
"</s>": 89,
"<mask>": 90
},
"unk_token": "<unk>"
}
}