five

Mechanistic-Anomaly-Detection/gemma2-jailbreaks

收藏
Hugging Face2024-09-20 更新2025-04-19 收录
下载链接:
https://hf-mirror.com/datasets/Mechanistic-Anomaly-Detection/gemma2-jailbreaks
下载链接
链接失效反馈
官方服务:
资源简介:
--- dataset_info: features: - name: prompt dtype: string - name: completion dtype: string splits: - name: benign_instructions_test num_bytes: 6275265 num_examples: 3973 - name: benign_instructions_train num_bytes: 18793864 num_examples: 11915 - name: circuit_breakers_test num_bytes: 2044537 num_examples: 1000 - name: circuit_breakers_train num_bytes: 6168825 num_examples: 3000 - name: harmful_autodan num_bytes: 457392 num_examples: 106 - name: harmful_gcg num_bytes: 130808 num_examples: 70 - name: harmful_human_mt num_bytes: 631949 num_examples: 77 - name: harmful_instructions_test num_bytes: 1170048 num_examples: 982 - name: harmful_instructions_train num_bytes: 3533225 num_examples: 2957 - name: harmful_msj num_bytes: 7632355 num_examples: 179 - name: harmful_pair num_bytes: 1099523 num_examples: 656 - name: harmful_prefill num_bytes: 206042 num_examples: 141 - name: mt_bench num_bytes: 243142 num_examples: 79 - name: or_bench_test num_bytes: 1281738 num_examples: 900 - name: or_bench_train num_bytes: 3880638 num_examples: 2738 - name: wildchat num_bytes: 2708363 num_examples: 494 - name: xstest num_bytes: 201526 num_examples: 230 download_size: 31053449 dataset_size: 56459240 configs: - config_name: default data_files: - split: benign_instructions_test path: data/benign_instructions_test-* - split: benign_instructions_train path: data/benign_instructions_train-* - split: circuit_breakers_test path: data/circuit_breakers_test-* - split: circuit_breakers_train path: data/circuit_breakers_train-* - split: harmful_autodan path: data/harmful_autodan-* - split: harmful_gcg path: data/harmful_gcg-* - split: harmful_human_mt path: data/harmful_human_mt-* - split: harmful_instructions_test path: data/harmful_instructions_test-* - split: harmful_instructions_train path: data/harmful_instructions_train-* - split: harmful_msj path: data/harmful_msj-* - split: harmful_pair path: data/harmful_pair-* - split: harmful_prefill path: data/harmful_prefill-* - split: mt_bench path: data/mt_bench-* - split: or_bench_test path: data/or_bench_test-* - split: or_bench_train path: data/or_bench_train-* - split: wildchat path: data/wildchat-* - split: xstest path: data/xstest-* ---
提供机构:
Mechanistic-Anomaly-Detection
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作