qd_tweet_convbert-base-turkish / tokenizer_config.json
Izzet's picture
add tokenizer
14d862a
raw history blame
No virus
413 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"name_or_path": "dbmdz/convbert-base-turkish-cased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "ConvBertTokenizer",
"unk_token": "[UNK]"
}