bert-base-spanish-wwm-uncased / special_tokens_map.json
josecannete's picture
updating all configs, adding both fast and legacy tokenizers, also adding tensorflow checkpoint for compatibility
27c33d2
raw
history blame
134 Bytes
{
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]"
}