Get the app
← back to catalog
AUTHOR

redsgnaoh

No models indexed under this account. Publishes 2 alignment datasets (1.7k downloads) tracked in our /datasets catalog.

Alignment datasets by redsgnaoh

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
orcaratgen 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are general, high-level explanation...
heal
980
orcaratspec 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are more specific, detailed explani...
heal
720
Dataset
Stage
Downloads
orcaratspec 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are more specific, detailed explani...
heal
720
orcaratgen 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are general, high-level explanation...
heal
980
Dataset
Stage
Downloads
orcaratgen 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are general, high-level explanation...
heal
980
orcaratspec 0 0
An rationale-enhanced version of the paired preference learning dataset Intel-ORCA-DPO. These rationales are more specific, detailed explani...
heal
720
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