{ "added_tokens_decoder": { "0": { "content": "[UNK]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19500": { "content": "[BOS]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19501": { "content": "[EOS]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19502": { "content": "[SEP]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19503": { "content": "[PAD]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19504": { "content": "[CLS]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19505": { "content": "[MASK]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false } }, "bos_token": "[BOS]", "clean_up_tokenization_spaces": false, "cls_token": "[CLS]", "eos_token": "[EOS]", "extra_special_tokens": {}, "mask_token": "[MASK]", "model_max_length": 1000000000000000019884624838656, "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "SmirkTokenizerFast", "tokenizer_file": "tokenizer.json", "unk_token": "[UNK]" }