PreferED / tokenizer_config.json
samagra14wefi's picture
Upload tokenizer
c1c3736
raw
history blame
520 Bytes
{
"bos_token": "[CLS]",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "[SEP]",
"mask_token": "[MASK]",
"max_length": 512,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"split_by_punct": false,
"stride": 0,
"tokenizer_class": "DebertaV2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]",
"vocab_type": "spm"
}