postagger-bio-portuguese / tokenizer_config.json
lisaterumi's picture
Upload tokenizer_config.json
2d34d57
raw
history blame contribute delete
559 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"name_or_path": "pucpr/biobertpt-all",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/transformers/d06bbe0fda9ebb9f6c4f5d8534f84d0c6b4c14dbbf3db080008e582a7caa9e61.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}