MIG_labor_lawformer / tokenizer_config.json
Wei-Jie's picture
Upload folder using huggingface_hub
a5cb1ff verified
raw
history blame contribute delete
No virus
469 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": true,
"eos_token": "</s>",
"errors": "replace",
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "LongformerTokenizer",
"trim_offsets": true,
"unk_token": "[UNK]"
}