Dialectal-Arabic-XLM-R-Base / tokenizer_config.json
3ebdola's picture
add tokenizer
9e11364
raw
history blame contribute delete
536 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
},
"model_max_length": 512,
"name_or_path": "Dialectal-Arabic-XLM-R-Base",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "Dialectal-Arabic-XLM-R-Base/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}