{ "add_prefix_space": true, "bos_token": { "__type": "AddedToken", "content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "clean_up_tokenization_spaces": true, "cls_token": { "__type": "AddedToken", "content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "entity_max_length": 8, "eos_token": { "__type": "AddedToken", "content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "errors": "replace", "marker_max_length": 128, "mask_token": { "__type": "AddedToken", "content": "<mask>", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false }, "model_max_length": 256, "pad_token": { "__type": "AddedToken", "content": "<pad>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "sep_token": { "__type": "AddedToken", "content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "tokenizer_class": "RobertaTokenizer", "trim_offsets": true, "unk_token": { "__type": "AddedToken", "content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false } }