{ "add_prefix_space": true, "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "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": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "5": { "content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "additional_special_tokens": [], "bos_token": "", "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": true, "eos_token": "", "extra_ids": 0, "legacy": true, "mask_token": "[MASK]", "model_max_length": 1024, "pad_token": "", "padding_side": "right", "processor_class": "LlavaProcessor", "sep_token": "[SEP]", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer", "unk_token": "" }