electra-restore-punctuation-turkish / tokenizer_config.json
uygarkurt's picture
Upload 6 files
b4d452e
raw
history blame
452 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"model_max_length": 512,
"name_or_path": "dbmdz/electra-base-turkish-cased-discriminator",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "ElectraTokenizer",
"unk_token": "[UNK]"
}