mbart-ja-en / tokenizer_config.json
ken11
init
bd1ceff
{"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": {}, "src_lang": "ja_XX", "tgt_lang": "en_XX", "additional_special_tokens": null, "max_length": 32, "max_target_length": 32, "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_class": "MBartTokenizer"}