bm-xlm-roberta-base / tokenizer_config.json
oza75's picture
Upload tokenizer
c553237 verified
raw
history blame contribute delete
405 Bytes
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"extra_special_tokens": [
"<s>",
"</s>"
],
"is_local": false,
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_id": 0,
"unk_token": "<unk>",
"use_fast": false
}