efontes-ner / tokenizer_config.json
jziebura's picture
Upload model auxiliary files
a91aae4 verified
raw
history blame
504 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"ignore_mismatched_sizes": true,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}