xlm-roberta-xxl / tokenizer_config.json
patrickvonplaten's picture
up
f003042
raw
history blame
475 Bytes
{"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": {}, "special_tokens_map_file": "./special_tokens_map.json", "name_or_path": "../xlm-roberta-xl/", "tokenizer_file": "../xlm-roberta-xl/tokenizer.json", "tokenizer_class": "XLMRobertaTokenizer"}