tokenizer_config.json

{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "clean_up_tokenization_spaces": true, "do_basic_tokenize": true, "model_max_length": 1000000000000000019884624838656, "never_split": null, "tokenizer_class": "BertTokenizer", "special_tokens_map_file": "/home/ifti001/.cache/huggingface/transformers/7cc9f436cefa78ab595ac4e5b35da41475c4703c7dfa70ca087711ea68d89a2f.7da70648c6cb9951e284c9685f9ba7ae083dd59ed1d6d84bdfc0584a4ea94b6d", "name_or_path": "LazarusNLP/simcse-indobert-base"}