Basque_Dialects_Classification / tokenizer_config.json
ikerHerrero's picture
Upload tokenizer
b3e3234
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"name_or_path": "ixa-ehu/roberta-eus-cc100-base-cased",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--ixa-ehu--roberta-eus-cc100-base-cased/snapshots/2769bc619bcbe1261f1e4a4012cf77c1ad601b40/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}