xlm-roberta-longformer-base-4096 / tokenizer_config.json
kdercksen's picture
Upload tokenizer
bdcb554
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "LongformerTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}