Alignment datasets by beatsprom

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.

3 in /datasets
Dataset
Stage
Downloads
cybersecurity-soc-threat-hunting-sft-dpo-2026 0 0
🛡️ Enterprise Cybersecurity AI, SOC Tier-3 & Threat Hunting SFT/DPO Dataset (2026) High-precision multi-turn instruction tuning and ...
376
ai-security-red-teaming-defense-2026 0 0
🛡️ AI Security, Red Teaming & Model Defense Dataset (2023–2026) Sample dataset of 30 audit-verified AI Security, Prompt Injection & Red ...
92
agentexploitdb 0 0
🛡️ AgentExploitDB: AI Agent & MCP Security Benchmark (2026) AgentExploitDB is an enterprise red-teaming benchmark and runtime defense ev...
68
Dataset
Stage
Downloads
agentexploitdb 0 0
🛡️ AgentExploitDB: AI Agent & MCP Security Benchmark (2026) AgentExploitDB is an enterprise red-teaming benchmark and runtime defense ev...
68
cybersecurity-soc-threat-hunting-sft-dpo-2026 0 0
🛡️ Enterprise Cybersecurity AI, SOC Tier-3 & Threat Hunting SFT/DPO Dataset (2026) High-precision multi-turn instruction tuning and ...
376
ai-security-red-teaming-defense-2026 0 0
🛡️ AI Security, Red Teaming & Model Defense Dataset (2023–2026) Sample dataset of 30 audit-verified AI Security, Prompt Injection & Red ...
92
Dataset
Stage
Downloads
cybersecurity-soc-threat-hunting-sft-dpo-2026 0 0
🛡️ Enterprise Cybersecurity AI, SOC Tier-3 & Threat Hunting SFT/DPO Dataset (2026) High-precision multi-turn instruction tuning and ...
376
ai-security-red-teaming-defense-2026 0 0
🛡️ AI Security, Red Teaming & Model Defense Dataset (2023–2026) Sample dataset of 30 audit-verified AI Security, Prompt Injection & Red ...
92
agentexploitdb 0 0
🛡️ AgentExploitDB: AI Agent & MCP Security Benchmark (2026) AgentExploitDB is an enterprise red-teaming benchmark and runtime defense ev...
68
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.

Open in Abliteration