Get the app
← back to catalog
AUTHOR

mvrcii

No models indexed under this account. Publishes 2 alignment datasets (497 downloads) tracked in our /datasets catalog.

Alignment datasets by mvrcii

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.

2 in /datasets
Dataset
Stage
Downloads
safety-harmful 0 0
Safety Harmful Corpus Overview 11,619 curated safety-critical prompts and responses from multiple red-teaming and adversar...
evaluate
276
safety-refusals 0 0
Safety Refusals Dataset Overview 17,450 safe refusal responses from LLMs, combining two safety evaluation benchmarks. All ...
evaluate
221
Dataset
Stage
Downloads
safety-harmful 0 0
Safety Harmful Corpus Overview 11,619 curated safety-critical prompts and responses from multiple red-teaming and adversar...
evaluate
276
safety-refusals 0 0
Safety Refusals Dataset Overview 17,450 safe refusal responses from LLMs, combining two safety evaluation benchmarks. All ...
evaluate
221
Dataset
Stage
Downloads
safety-harmful 0 0
Safety Harmful Corpus Overview 11,619 curated safety-critical prompts and responses from multiple red-teaming and adversar...
evaluate
276
safety-refusals 0 0
Safety Refusals Dataset Overview 17,450 safe refusal responses from LLMs, combining two safety evaluation benchmarks. All ...
evaluate
221
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