MiniLM-L6-danish-encoder / tokenizer_config.json
KennethTM's picture
initial upload
af75341
raw
history blame
485 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 512,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]",
"vocab": "bert-uncased-tokenizer-danish/vocab.txt"
}