dummy-phi3-test / tokenizer.json
AlonKellner-Jounce's picture
vocab size 25
b7fc258 verified
raw
history blame
3.14 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 1,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 2,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 3,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "NFD"
},
{
"type": "Lowercase"
},
{
"type": "StripAccents"
}
]
},
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Whitespace"
},
{
"type": "Digits",
"individual_digits": true
}
]
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "[CLS]",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "[SEP]",
"type_id": 1
}
}
],
"special_tokens": {
"[CLS]": {
"id": "[CLS]",
"ids": [
1
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
2
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[UNK]": 0,
"[CLS]": 1,
"[SEP]": 2,
"[PAD]": 3,
"[MASK]": 4,
"boken": 5,
"coken": 6,
"doken": 7,
"foken": 8,
"goken": 9,
"hoken": 10,
"joken": 11,
"koken": 12,
"loken": 13,
"moken": 14,
"noken": 15,
"poken": 16,
"qoken": 17,
"roken": 18,
"soken": 19,
"token": 20,
"voken": 21,
"woken": 22,
"xoken": 23,
"yoken": 24
},
"unk_token": "[UNK]"
}
}