serengeti / tokenizer_config.json
elmadany
commit from elmadany
e28f9b3
raw
history blame
514 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "/home/elmadany/afircan_langauges/new_models/NLU_models/XMLR@4",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>",
"use_fast": true
}