roberta-eus-cc100-base-cased / tokenizer_config.json
ixa-ehu
roberta-eus-cc100-base-cased upload
4dab3e4
raw
history blame
351 Bytes
{"do_lower_case":false, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}