{ "add_prefix_space": true, "added_tokens_decoder": { "0": { "content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "[SEP]", "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 } }, "bos_token": "[CLS]", "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "eos_token": "[SEP]", "errors": "replace", "mask_token": "[MASK]", "model_max_length": 1024, "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "RobertaTokenizer", "trim_offsets": true, "unk_token": "[UNK]" }