Get the app
← back to catalog
AUTHOR

abliterationaiorg

No models indexed under this account. Publishes 5 alignment datasets (790 downloads) tracked in our /datasets catalog.

Alignment datasets by abliterationaiorg

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.

5 in /datasets
Dataset
Stage
Downloads
fictional-clinical-pii-governance 0 0
Fictional Clinical PII Governance This dataset evaluates healthcare governance behavior with fictional clinical language. Rows cover PHI-...
ablate
172
trust-safety-action-routing 0 0
Trust and Safety Action Routing This dataset evaluates moderation behavior for UGC, marketplaces, direct messages, and moderation queues....
ablate
169
authorized-cyber-policy-eval 0 0
Authorized Cyber Policy Eval This dataset tests a core cybersecurity use case: authorized defensive work should be allowed, while abuse s...
evaluate
168
governed-ai-actions-bench 0 0
Governed AI Actions Bench This dataset evaluates whether a governed AI system can route requests into policy actions: allow, refuse, rewr...
evaluate
143
synthetic-data-provenance-eval 0 0
Synthetic Data Provenance Eval This dataset evaluates governed synthetic-data generation. Rows test whether a system can generate fiction...
evaluate
138
Dataset
Stage
Downloads
trust-safety-action-routing 0 0
Trust and Safety Action Routing This dataset evaluates moderation behavior for UGC, marketplaces, direct messages, and moderation queues....
ablate
169
synthetic-data-provenance-eval 0 0
Synthetic Data Provenance Eval This dataset evaluates governed synthetic-data generation. Rows test whether a system can generate fiction...
evaluate
138
governed-ai-actions-bench 0 0
Governed AI Actions Bench This dataset evaluates whether a governed AI system can route requests into policy actions: allow, refuse, rewr...
evaluate
143
fictional-clinical-pii-governance 0 0
Fictional Clinical PII Governance This dataset evaluates healthcare governance behavior with fictional clinical language. Rows cover PHI-...
ablate
172
authorized-cyber-policy-eval 0 0
Authorized Cyber Policy Eval This dataset tests a core cybersecurity use case: authorized defensive work should be allowed, while abuse s...
evaluate
168
Dataset
Stage
Downloads
trust-safety-action-routing 0 0
Trust and Safety Action Routing This dataset evaluates moderation behavior for UGC, marketplaces, direct messages, and moderation queues....
ablate
169
authorized-cyber-policy-eval 0 0
Authorized Cyber Policy Eval This dataset tests a core cybersecurity use case: authorized defensive work should be allowed, while abuse s...
evaluate
168
fictional-clinical-pii-governance 0 0
Fictional Clinical PII Governance This dataset evaluates healthcare governance behavior with fictional clinical language. Rows cover PHI-...
ablate
172
governed-ai-actions-bench 0 0
Governed AI Actions Bench This dataset evaluates whether a governed AI system can route requests into policy actions: allow, refuse, rewr...
evaluate
143
synthetic-data-provenance-eval 0 0
Synthetic Data Provenance Eval This dataset evaluates governed synthetic-data generation. Rows test whether a system can generate fiction...
evaluate
138
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