Get the app
← back to catalog
AUTHOR

Faruna01

No models indexed under this account. Publishes 2 alignment datasets (888 downloads) tracked in our /datasets catalog.

Alignment datasets by Faruna01

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
lsr-anchoring-phase2-results 0 0
LSR Anchoring — Multilingual Benchmark & Safety Steering Results This dataset contains all experimental results for two related studies: ...
ablate
480
lsr-benchmark 0 0
LSR Benchmark: Linguistic Safety Robustness for West African Languages Dataset Description Homepage: https://huggingface.c...
evaluate
408
Dataset
Stage
Downloads
lsr-anchoring-phase2-results 0 0
LSR Anchoring — Multilingual Benchmark & Safety Steering Results This dataset contains all experimental results for two related studies: ...
ablate
480
lsr-benchmark 0 0
LSR Benchmark: Linguistic Safety Robustness for West African Languages Dataset Description Homepage: https://huggingface.c...
evaluate
408
Dataset
Stage
Downloads
lsr-anchoring-phase2-results 0 0
LSR Anchoring — Multilingual Benchmark & Safety Steering Results This dataset contains all experimental results for two related studies: ...
ablate
480
lsr-benchmark 0 0
LSR Benchmark: Linguistic Safety Robustness for West African Languages Dataset Description Homepage: https://huggingface.c...
evaluate
408
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