{ "added_tokens_decoder": { "0": { "content": "[UNK]", "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": "[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 }, "5": { "content": "[DOMAIN]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "[PATH]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "7": { "content": "[IP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "8": { "content": "[IPv6]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [ "[DOMAIN]", "[PATH]", "[IP]", "[IPv6]" ], "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "mask_token": "[MASK]", "model_max_length": 1024, "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "PreTrainedTokenizerFast", "unk_token": "[UNK]" }