dta-char-ngram / tokenizer.json
stefan-it's picture
feat: add initial model
b719bdf verified
Raw
History Blame Contribute Delete
8.44 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<eos>",
"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": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"String": "⸗\n"
},
"content": ""
},
{
"type": "Replace",
"pattern": {
"String": "-\n"
},
"content": ""
},
{
"type": "NFC"
},
{
"type": "Replace",
"pattern": {
"Regex": "(?<=\\p{L}\\p{M}*)Σ(?!\\p{M}*\\p{L})"
},
"content": "ς"
},
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"String": "aͤ"
},
"content": "ä"
},
{
"type": "Replace",
"pattern": {
"String": "oͤ"
},
"content": "ö"
},
{
"type": "Replace",
"pattern": {
"String": "uͤ"
},
"content": "ü"
},
{
"type": "Replace",
"pattern": {
"String": "ͤ"
},
"content": ""
},
{
"type": "Replace",
"pattern": {
"String": "ſ"
},
"content": "s"
},
{
"type": "Replace",
"pattern": {
"String": "ꝛ"
},
"content": "r"
},
{
"type": "Replace",
"pattern": {
"String": "⸗"
},
"content": "-"
},
{
"type": "Replace",
"pattern": {
"String": "„"
},
"content": "\""
},
{
"type": "Replace",
"pattern": {
"String": "“"
},
"content": "\""
},
{
"type": "Replace",
"pattern": {
"String": "”"
},
"content": "\""
},
{
"type": "Replace",
"pattern": {
"String": "»"
},
"content": "\""
},
{
"type": "Replace",
"pattern": {
"String": "«"
},
"content": "\""
},
{
"type": "Replace",
"pattern": {
"String": "‘"
},
"content": "'"
},
{
"type": "Replace",
"pattern": {
"String": "’"
},
"content": "'"
},
{
"type": "Replace",
"pattern": {
"String": "‚"
},
"content": "'"
},
{
"type": "Replace",
"pattern": {
"String": "–"
},
"content": "-"
},
{
"type": "Replace",
"pattern": {
"String": "—"
},
"content": "-"
},
{
"type": "Replace",
"pattern": {
"Regex": "\\d"
},
"content": "0"
},
{
"type": "Replace",
"pattern": {
"Regex": "\\s+"
},
"content": " "
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "[\\s\\S]"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {}
},
"decoder": {
"type": "Fuse"
},
"model": {
"type": "WordLevel",
"vocab": {
"<eos>": 0,
"<unk>": 1,
" ": 2,
"e": 3,
"n": 4,
"i": 5,
"r": 6,
"s": 7,
"t": 8,
"a": 9,
"d": 10,
"h": 11,
"l": 12,
"u": 13,
"c": 14,
"g": 15,
"m": 16,
"o": 17,
"b": 18,
"w": 19,
"f": 20,
",": 21,
".": 22,
"0": 23,
"z": 24,
"k": 25,
"v": 26,
"p": 27,
"ü": 28,
"ä": 29,
"/": 30,
"ß": 31,
"ö": 32,
"j": 33,
"y": 34,
"-": 35,
")": 36,
";": 37,
"(": 38,
":": 39,
"\"": 40,
"x": 41,
"q": 42,
"'": 43,
"!": 44,
"_": 45,
"?": 46,
"¬": 47,
"*": 48,
"§": 49,
"=": 50,
"é": 51,
"æ": 52,
"‒": 53,
"&": 54,
"]": 55,
"α": 56,
"ñ": 57,
"[": 58,
"ν": 59,
"ο": 60,
"ẽ": 61,
"τ": 62,
"ι": 63,
"ε": 64,
"+": 65,
"ς": 66,
"̃": 67,
"â": 68,
"à": 69,
"è": 70,
"σ": 71,
"ô": 72,
"π": 73,
"μ": 74,
"λ": 75,
"ê": 76,
"ρ": 77,
"κ": 78,
"ë": 79,
"°": 80,
"½": 81,
"·": 82,
"î": 83,
"δ": 84,
"á": 85,
"†": 86,
"υ": 87,
"γ": 88,
"‟": 89,
"…": 90,
"ͦ": 91,
"ί": 92,
"⁾": 93,
"ω": 94,
"η": 95,
"œ": 96,
"φ": 97,
"β": 98,
"ϑ": 99,
"û": 100,
"%": 101,
"í": 102,
"έ": 103,
"ἀ": 104,
"ά": 105,
"ό": 106,
"ἐ": 107,
"ů": 108,
"ϱ": 109,
"χ": 110,
"′": 111,
"č": 112,
"ò": 113,
"ç": 114,
"́": 115,
"ʒ": 116,
"¼": 117,
"|": 118,
"ὸ": 119,
"ὶ": 120,
"": 121,
"─": 122,
"ó": 123,
"̄": 124,
"ύ": 125,
"ù": 126,
"ï": 127,
"ṅ": 128,
"þ": 129,
"ĕ": 130,
"ῖ": 131,
"″": 132,
"ā": 133,
"⋹": 134,
"¾": 135,
"¹": 136,
"ũ": 137,
"ú": 138,
"ή": 139,
"ῦ": 140,
"θ": 141,
"ῶ": 142,
"š": 143,
"×": 144,
"ē": 145,
"ξ": 146,
"ὰ": 147,
"ý": 148,
"ɟ": 149,
"õ": 150,
"̅": 151,
"ἰ": 152,
"ø": 153,
"ζ": 154,
"ž": 155,
"²": 156,
"〃": 157,
"ῆ": 158,
"ꝟ": 159,
"ã": 160,
"ὴ": 161,
"℔": 162,
"ꝙ": 163,
"ὐ": 164,
"̆": 165,
"⅓": 166,
"¶": 167,
"ἔ": 168,
"£": 169,
"å": 170,
"│": 171,
"⁽": 172,
"³": 173,
"□": 174,
"℥": 175,
"ϰ": 176,
"ώ": 177,
"ψ": 178,
"⁴": 179,
"∞": 180,
"ř": 181,
"ἄ": 182,
"ę": 183,
"ŭ": 184,
"⅔": 185,
"ὲ": 186,
"ĭ": 187,
"⁵": 188,
"℞": 189,
"ÿ": 190,
"ū": 191,
"⁶": 192,
"⏑": 193,
"#": 194,
"≠": 195,
"̶": 196,
"ὁ": 197,
"√": 198,
"⁷": 199,
"ὑ": 200,
"ī": 201,
"ì": 202,
"⁸": 203,
"ἱ": 204,
"⁹": 205,
"ἡ": 206,
"ð": 207,
"ł": 208,
"̕": 209,
"ʼ": 210,
"⃛": 211,
"}": 212,
"☉": 213,
"{": 214,
"ą": 215,
"ὀ": 216,
"〟": 217,
"ś": 218,
"ῳ": 219,
"₤": 220,
"ὺ": 221,
"⁰": 222,
"ῷ": 223,
"‥": 224,
"⅛": 225,
"ᾶ": 226,
"ō": 227,
"ă": 228,
"ὅ": 229,
"∫": 230,
"ἑ": 231,
"‰": 232,
"ŷ": 233,
"ż": 234,
">": 235,
"ἴ": 236,
"℈": 237,
"<": 238,
"ě": 239,
"‧": 240,
"♂": 241,
"♀": 242,
"ď": 243,
"ḱ": 244,
"⅕": 245,
"᾽": 246,
"ὄ": 247,
"⅜": 248,
"ˈ": 249,
"ć": 250,
"˙": 251,
"ῥ": 252,
"ἁ": 253,
"‴": 254,
"•": 255
},
"unk_token": "<unk>"
}
}