duyguanalizison25 / tokenizer.json
asude55's picture
Create tokenizer.json
83a37d9 verified
raw
history blame
2.07 kB
{
"version": "0.1",
"truncation": {
"max_length": 512,
"stride": 0,
"strategy": "longest_first"
},
"padding": {
"strategy": "longest",
"max_length": 512,
"pad_to_multiple_of": 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": false
},
"pre_tokenizer": {
"type": "BertPreTokenizer"
},
"post_processor": {
"type": "BertPostProcessor",
"sep": {
"type": "AddedToken",
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
"cls": {
"type": "AddedToken",
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
}
},
"decoder": {
"type": "WordPiece",
"cleanup": true
},
"model": {
"type": "WordPiece",
"unk_token": "[UNK]",
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"hello": 5,
"world": 6
},
"max_input_chars_per_word": 100
}
}