koelectra-dialect-v1 / tokenizer_config.json
rippertnt's picture
Upload tokenizer
dbad6ae
raw
history blame contribute delete
668 Bytes
{
"additional_special_tokens": [
"[NAME]",
"[RELIGION]"
],
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"model_max_length": 512,
"name_or_path": "monologg/koelectra-base-v3-goemotions",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/circulus/.cache/huggingface/hub/models--monologg--koelectra-base-v3-goemotions/snapshots/9b9385c0190252577bc51bf222426e726fea51d0/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "ElectraTokenizer",
"unk_token": "[UNK]"
}