numberwang / tokenizer.json
graafhenk's picture
WangNet: character-level Numberwang classifier
f0278af verified
Raw History Blame Contribute Delete
3 kB
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 64,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 64
},
"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": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"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
}
],
"normalizer": {
"type": "Lowercase"
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "."
},
"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": null,
"model": {
"type": "WordLevel",
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
" ": 5,
"$": 6,
"%": 7,
"'": 8,
"(": 9,
")": 10,
"*": 11,
"+": 12,
",": 13,
"-": 14,
".": 15,
"/": 16,
"0": 17,
"1": 18,
"2": 19,
"3": 20,
"4": 21,
"5": 22,
"6": 23,
"7": 24,
"8": 25,
"9": 26,
":": 27,
"a": 28,
"b": 29,
"c": 30,
"d": 31,
"e": 32,
"f": 33,
"g": 34,
"h": 35,
"i": 36,
"j": 37,
"k": 38,
"l": 39,
"m": 40,
"n": 41,
"o": 42,
"p": 43,
"q": 44,
"r": 45,
"s": 46,
"t": 47,
"u": 48,
"v": 49,
"w": 50,
"x": 51,
"y": 52,
"z": 53,
"£": 54,
"ß": 55,
"ä": 56,
"å": 57,
"é": 58,
"ê": 59,
"ë": 60,
"ó": 61,
"ö": 62,
"ü": 63,
"ą": 64,
"ć": 65,
"ę": 66,
"ś": 67,
"€": 68
},
"unk_token": "[UNK]"
}
}