16 lines
354 B
JSON
16 lines
354 B
JSON
{
|
|
"add_prefix_space": true,
|
|
"backend": "tokenizers",
|
|
"bos_token": "<s>",
|
|
"clean_up_tokenization_spaces": true,
|
|
"cls_token": "<s>",
|
|
"eos_token": "</s>",
|
|
"is_local": false,
|
|
"mask_token": "<mask>",
|
|
"model_max_length": 512,
|
|
"pad_token": "<pad>",
|
|
"sep_token": "</s>",
|
|
"tokenizer_class": "XLMRobertaTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|