WRAP / tokenizer_config.json
TomatenMarc's picture
Upload 9 files
c2ec47d
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 128,
"normalization": false,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "BertweetTokenizer",
"unk_token": "<unk>"
}