corpus-refiner-jp / tokenizer_config.json
MIyamoto Keisuke
Upload trained corpus-refiner-jp model
84bafb1 verified
Raw
History Blame Contribute Delete
713 Bytes
{
"add_dummy_prefix_space": false,
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<cls>",
"do_lower_case": false,
"eos_token": "</s>",
"extra_ids": 0,
"extra_special_tokens": [
"<line>"
],
"is_local": true,
"keep_accents": true,
"legacy": false,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "right",
"sep_token": "<sep>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"use_default_system_prompt": false
}