Xenova's picture
Xenova HF staff
Upload tokenizer.json with huggingface_hub
acd5f97
raw
history blame
2.33 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 45,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^7avc\u201405\u00f38pyz4m\u00fcks\u00e1qhn\u00e9_91ft xd\u00edb3jgl2iue\u00fao\u00f1r6]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "7"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"7": 0,
"a": 1,
"v": 2,
"c": 3,
"\u2014": 4,
"0": 5,
"5": 6,
"\u00f3": 7,
"8": 8,
"p": 9,
"y": 10,
"z": 11,
"4": 12,
"m": 13,
"\u00fc": 14,
"k": 15,
"s": 16,
"\u00e1": 17,
"q": 18,
"h": 19,
"n": 20,
"\u00e9": 21,
"_": 22,
"9": 23,
"1": 24,
"f": 25,
"t": 26,
" ": 27,
"x": 28,
"d": 29,
"\u00ed": 30,
"b": 31,
"3": 32,
"j": 33,
"g": 34,
"l": 35,
"2": 36,
"i": 37,
"u": 38,
"e": 39,
"\u00fa": 40,
"o": 41,
"\u00f1": 42,
"r": 43,
"6": 44,
"<unk>": 45
}
}
}