full_chinese_bert / tokenizer_config.json
timorobrecht's picture
Upload folder using huggingface_hub
1a91333 verified
Raw
History Blame Contribute Delete
1.43 kB
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"14": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"tokenization_pinyin_code.EncodedMandarinTokenizer",
null
]
},
"backend": "custom",
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"eos_token": "[SEP]",
"jieba": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"pinyin_format": "pinyin-code",
"sep_token": "[SEP]",
"tokenizer_class": "EncodedMandarinTokenizer",
"transliteration": "pinyin-code",
"unk_token": "[UNK]",
"use_jieba": true
}