Arkhiveus/UnAligner-Llama3-8B
4 files
↓ 15
♥ 0
AUTHOR
2 models in the catalog. 28 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 4 alignment datasets (1.5k downloads).
Alignment datasets by
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.
Dataset
Stage
Downloads
Likes
unaligner1K 0 0
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, ToxicQAFinal.
The datasets were sorted...
367
1
toxic-dpo-v0.2-HarmSorted 0 0
toxic-dpo-v0.2, sorted by safety and harm category using Llama-Guard-2 .
361
2
unaligner1K_DPO 0 0
DPO only version of unaligner1K
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, Tox...
359
1
Dataset
Stage
Downloads
Likes
toxic-dpo-v0.2-HarmSorted 0 0
toxic-dpo-v0.2, sorted by safety and harm category using Llama-Guard-2 .
361
2
unaligner1K_DPO 0 0
DPO only version of unaligner1K
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, Tox...
359
1
unaligner1K 0 0
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, ToxicQAFinal.
The datasets were sorted...
367
1
Dataset
Stage
Downloads
Likes
toxic-dpo-v0.2-HarmSorted 0 0
toxic-dpo-v0.2, sorted by safety and harm category using Llama-Guard-2 .
361
2
unaligner1K 0 0
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, ToxicQAFinal.
The datasets were sorted...
367
1
unaligner1K_DPO 0 0
DPO only version of unaligner1K
A consolidated and cleaned dataset created from toxic-dpo-v0.2, orthogonal-activation-steering-TOXIC, Tox...
359
1