tokenizer / tokenizer.json
officialamit558's picture
Upload tokenizer
b4a227f verified
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 128,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 128
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 57,
"pad_type_id": 0,
"pad_token": "[PAD]"
},
"added_tokens": [
{
"id": 57,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 58,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 59,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 60,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 61,
"content": "[UNK]",
"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": [
59
],
"tokens": [
"[CLS]"
]
},
"[SEP]": {
"id": "[SEP]",
"ids": [
60
],
"tokens": [
"[SEP]"
]
}
}
},
"decoder": {
"type": "WordPiece",
"prefix": "##",
"cleanup": true
},
"model": {
"type": "WordPiece",
"unk_token": "[UNK]",
"continuing_subword_prefix": "##",
"max_input_chars_per_word": 100,
"vocab": {
"a": 0,
"b": 1,
"c": 2,
"d": 3,
"e": 4,
"f": 5,
"g": 6,
"h": 7,
"i": 8,
"j": 9,
"k": 10,
"l": 11,
"m": 12,
"n": 13,
"o": 14,
"p": 15,
"q": 16,
"r": 17,
"s": 18,
"t": 19,
"u": 20,
"v": 21,
"w": 22,
"x": 23,
"y": 24,
"z": 25,
"A": 26,
"B": 27,
"C": 28,
"D": 29,
"E": 30,
"F": 31,
"G": 32,
"H": 33,
"I": 34,
"J": 35,
"K": 36,
"L": 37,
"M": 38,
"N": 39,
"O": 40,
"P": 41,
"Q": 42,
"R": 43,
"S": 44,
"T": 45,
"U": 46,
"V": 47,
"W": 48,
"X": 49,
"Y": 50,
"Z": 51,
" ": 52,
".": 53,
",": 54,
"!": 55,
"?": 56,
"[PAD]": 57,
"[MASK]": 58,
"[CLS]": 59,
"[SEP]": 60,
"[UNK]": 61
}
}
}