finetuned_bert3_jcommon / tokenizer_config.json
hama3's picture
Upload tokenizer
b046c5c verified
{
"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
},
"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
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"do_subword_tokenize": true,
"do_word_tokenize": true,
"jumanpp_kwargs": null,
"mask_token": "[MASK]",
"mecab_kwargs": {
"mecab_dic": "unidic_lite"
},
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"subword_tokenizer_type": "wordpiece",
"sudachi_kwargs": null,
"tokenizer_class": "BertJapaneseTokenizer",
"unk_token": "[UNK]",
"word_tokenizer_type": "mecab"
}