ease-xlm-roberta-base / tokenizer_config.json
sosuke's picture
add tokenizer
c0b425e
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "results/my-unsup-mease-data-typehn-18-langs-avg-xlm-roberta-base-best", "special_tokens_map_file": "results/my-unsup-mease-data-typehn-18-langs-avg-xlm-roberta-base-best/special_tokens_map.json", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}