hupd_mlm_distilroberta / tokenizer_config.json
cfcooney's picture
Upload tokenizer
a1da2ee
raw
history blame contribute delete
351 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}