{ "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 }, "250001": { "content": "<mask>", "lstrip": true, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "<s>", "clean_up_tokenization_spaces": true, "cls_token": "<s>", "cls_token_box": [ 0, 0, 0, 0 ], "eos_token": "</s>", "mask_token": "<mask>", "model_max_length": 1000000000000000019884624838656, "only_label_first_subword": true, "pad_token": "<pad>", "pad_token_box": [ 0, 0, 0, 0 ], "pad_token_label": -100, "sep_token": "</s>", "sep_token_box": [ 1000, 1000, 1000, 1000 ], "sp_model_kwargs": {}, "tokenizer_class": "LayoutXLMTokenizer", "unk_token": "<unk>" }