roberta-long-japanese / tokenizer_config.json
hiroshi-matsuda-rit's picture
add files
649e86b
raw
history blame contribute delete
541 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"keep_accents": true,
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "nlp-waseda/roberta-base-japanese",
"pad_token": "[PAD]",
"remove_space": true,
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "AlbertTokenizer",
"unk_token": "[UNK]"
}