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": 512, "special_tokens_map_file": "/home/terry/.cache/huggingface/transformers/c16ddb837f144c02d3d2981da39e666f56f39c995926bc538f9e5946f166a113.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "uer/chinese_roberta_L-4_H-512", "tokenizer_class": "BertTokenizer"}