guwen-seg / tokenizer_config.json
ethanyt's picture
init
543afa4
raw
history blame
379 Bytes
{"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, "use_fast": true, "special_tokens_map_file": "models/guwenbert-base-fs/special_tokens_map.json", "name_or_path": "models/guwenbert-base-fs", "do_basic_tokenize": true, "never_split": null}