Legal-BERTimbau-sts-large / tokenizer_config.json
Rui Melo
initial commit
dda1e5e
raw
history blame
542 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"name_or_path": "Legal_SBERT/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ruimelo/.cache/huggingface/transformers/d5b721c156180bbbcc4a1017e8c72a18f8f96cdc178acec5ddcd45905712b4cf.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}