{ "added_tokens_decoder": { "0": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "[UNK]", "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": "[BOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}, "6": {"content": "[EOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true} }, "auto_map": { "AutoTokenizer": ["tokenizer.NucEL_Tokenizer", null] }, "k": 1, "bos_token": "[BOS]", "clean_up_tokenization_spaces": false, "cls_token": "[CLS]", "eos_token": "[EOS]", "extra_special_tokens": {}, "mask_token": "[MASK]", "model_max_length": 2048, "pad_token": "[PAD]", "sep_token": "[SEP]", "tokenizer_class": "NucEL_Tokenizer", "unk_token": "[UNK]" }