{ "added_tokens_decoder": { "50000": { "content": "[BOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50001": { "content": "[EOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50002": { "content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50003": { "content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50004": { "content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50005": { "content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50006": { "content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "[BOS]", "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "eos_token": "[EOS]", "mask_token": "[MASK]", "model_max_length": 1024, "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "PreTrainedTokenizerFast", "unk_token": "[UNK]" }