bert-large-portuguese-cased-sts / tokenizer_config.json
Rui Melo
initial commit
05751e7
raw
history blame
553 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"name_or_path": "/home/ruimelo/.cache/torch/sentence_transformers/neuralmind_bert-large-portuguese-cased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ruimelo/.cache/torch/sentence_transformers/neuralmind_bert-large-portuguese-cased/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}