tokenizer_config.json

{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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": 2048, "special_tokens_map_file": null, "name_or_path": "cointegrated/rubert-tiny2", "padding": true, "truncation": true, "tokenizer_file": "/root/.cache/huggingface/transformers/cfa6d82dc8ecc7fe3f06deb449f38968cdd188bb84c8da0e06f0bbfddbede1e3.550ab7157d36210bf96c7c3b30e621933d37d635c5f2e290f7e88bd5f7c9198a", "tokenizer_class": "BertTokenizer"}