tiny-embedding-test / tokenizer.json
0neisall's picture
Upload folder using huggingface_hub
a225491 verified
Raw History Blame Contribute Delete
3.67 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"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": "BertNormalizer",
"clean_text": true,
"handle_chinese_chars": true,
"strip_accents": null,
"lowercase": true
},
"pre_tokenizer": {
"type": "BertPreTokenizer"
},
"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": [
2
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
3
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"model": {
"type": "WordPiece",
"unk_token": "[UNK]",
"continuing_subword_prefix": "##",
"max_input_chars_per_word": 100,
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"a": 5,
"b": 6,
"c": 7,
"d": 8,
"e": 9,
"f": 10,
"g": 11,
"h": 12,
"i": 13,
"j": 14,
"k": 15,
"l": 16,
"m": 17,
"n": 18,
"o": 19,
"p": 20,
"q": 21,
"r": 22,
"s": 23,
"t": 24,
"u": 25,
"v": 26,
"w": 27,
"x": 28,
"y": 29,
"z": 30,
"0": 31,
"1": 32,
"2": 33,
"3": 34,
"4": 35,
"5": 36,
"6": 37,
"7": 38,
"8": 39,
"9": 40,
"hello": 41,
"world": 42,
"test": 43,
"embedding": 44,
"simple": 45,
"model": 46,
"你": 47,
"好": 48,
"世": 49,
"界": 50,
"测": 51,
"试": 52,
"模": 53,
"型": 54,
"向": 55,
"量": 56,
"这": 57,
"是": 58,
"一": 59,
"个": 60,
".": 61,
",": 62,
"!": 63,
"?": 64
}
}
}