{ "added_tokens_decoder": { "0": { "content": "<s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "<pad>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "</s>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "<unk>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "<mask>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [], "bos_token": "<s>", "clean_up_tokenization_spaces": true, "cls_token": "<s>", "do_lowercase_and_remove_accent": false, "id2lang": null, "lang2id": null, "mask_token": "<mask>", "max_length": 512, "model_max_length": 512, "pad_to_multiple_of": null, "pad_token": "<pad>", "pad_token_type_id": 0, "padding_side": "right", "sep_token": "</s>", "stride": 0, "tokenizer_class": "HerbertTokenizer", "truncation_side": "right", "truncation_strategy": "longest_first", "unk_token": "<unk>" }