{ "add_prefix_space": false, "bos_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "cls_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "eos_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "errors": "replace", "mask_token": { "__type": "AddedToken", "content": "", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false }, "max_len": 512, "name_or_path": "/data/roberta_indo/", "pad_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "sep_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false }, "special_tokens_map_file": null, "tokenizer_class": "RobertaTokenizer", "trim_offsets": true, "unk_token": { "__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false } }