{ "add_prefix_space": false, "added_tokens_decoder": { "0": { "content": "[UNK]", "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": "[PAD]", "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": "[START]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "556": { "content": "[END]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "[START]", "bos_token_id": 5, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "cls_token_id": 1, "eos_token": "[END]", "eos_token_id": 556, "mask_token": "[MASK]", "mask_token_id": 4, "model_max_len": 4096, "model_max_length": 4096, "pad_token": "[PAD]", "pad_token_id": 3, "seo_token_id": 2, "sep_token": "[SEP]", "tokenizer_class": "PreTrainedTokenizerFast", "type": "Split", "unk_token": "[UNK]", "unk_token_id": 0 }