koroberta-large-lkm / tokenizer_config.json
korca's picture
first commit
ddc855e
raw
history blame
624 Bytes
{
"bos_token": "[CLS]",
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "klue/roberta-large",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/Users/1112359/.cache/huggingface/transformers/1a24ab4628028ed80dea35ce3334a636dc656fd9a17a09bad377f88f0cbecdac.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}