KR-Roberta-large-v1 / tokenizer_config.json
Junmai's picture
add tokenizer
f5b0a21
raw
history blame
550 Bytes
{
"already_has_special_tokens": true,
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "./KR_ROBERTA_39",
"pad_token": "<pad>",
"padding_side": "right",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "./KR_ROBERTA_39/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}