{ "added_tokens_decoder": { "0": { "content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "[SEP]", "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 }, "32000": { "content": "[Q] ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "32001": { "content": "[D] ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false } }, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_basic_tokenize": true, "do_lower_case": true, "extra_special_tokens": {}, "mask_token": "[MASK]", "max_len": 8192, "max_length": 8192, "model_input_names": [ "input_ids", "attention_mask" ], "model_max_length": 8192, "never_split": null, "pad_to_multiple_of": null, "pad_token": "[MASK]", "pad_token_type_id": 0, "padding_side": "right", "sep_token": "[SEP]", "stride": 0, "strip_accents": false, "tokenize_chinese_chars": true, "tokenizer_class": "PreTrainedTokenizerFast", "truncation_side": "right", "truncation_strategy": "longest_first", "unk_token": "[UNK]" }