Get the app
← back to catalog
AUTHOR

uninhibited-scholar

No models indexed under this account. Publishes 1 alignment dataset (111 downloads) tracked in our /datasets catalog.

Alignment datasets by uninhibited-scholar

Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.

1 in /datasets
Dataset
Stage
Downloads
defensive-refusal-bench-zh 0 0
defensive-refusal-bench-zh · 中文网安「防御问题误拒」评测基准 测安全对齐模型是否把正当防御/安全教育问题也误拒（over-refusal），用真实危害请求作对照防刷分。与 agent-safety-bench-zh 互补："该拦的拦没拦住" v...
evaluate
111
Dataset
Stage
Downloads
defensive-refusal-bench-zh 0 0
defensive-refusal-bench-zh · 中文网安「防御问题误拒」评测基准 测安全对齐模型是否把正当防御/安全教育问题也误拒（over-refusal），用真实危害请求作对照防刷分。与 agent-safety-bench-zh 互补："该拦的拦没拦住" v...
evaluate
111
Dataset
Stage
Downloads
defensive-refusal-bench-zh 0 0
defensive-refusal-bench-zh · 中文网安「防御问题误拒」评测基准 测安全对齐模型是否把正当防御/安全教育问题也误拒（over-refusal），用真实危害请求作对照防刷分。与 agent-safety-bench-zh 互补："该拦的拦没拦住" v...
evaluate
111
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration