deberta-tokenizer / tokenizer_config.json
stefan-it's picture
tokenizer: add initial config
3dc595a
raw
history blame contribute delete
452 Bytes
{
"do_lower_case": false,
"bos_token": "[CLS]",
"eos_token": "[SEP]",
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"split_by_punct": false,
"special_tokens_map_file": null,
"name_or_path": "gwlms/deberta-tokenizer",
"sp_model_kwargs": {},
"tokenizer_file": null,
"tokenizer_class": "DebertaV2Tokenizer",
"vocab_type": "spm"
}