koMHBERT-kcbert-based-v2 / tokenizer_config.json
eunjin's picture
kcbert based version2
f932b4a
raw
history blame contribute delete
388 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 300, "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/class/project/KoMHBERT_build/kcbert-psyart-based", "do_basic_tokenize": true, "never_split": null}