roformer_chinese_base / tokenizer_config.json
junnyu's picture
Create tokenizer_config.json
e4b0463
raw
history blame
471 Bytes
{
"do_lower_case": true,
"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": 1536,
"special_tokens_map_file": null,
"tokenizer_file": null,
"name_or_path": "junnyu/roformer_chinese_base",
"tokenizer_class": "RoFormerTokenizer"
}