Get the app
← back to catalog
AUTHOR

jkminder

No models indexed under this account. Publishes 4 alignment datasets (1k downloads) tracked in our /datasets catalog.

Alignment datasets by jkminder

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.

4 in /datasets
Dataset
Stage
Downloads
xstest-overrefusal 0 0
XSTest — Over-Refusal Subset A filtered subset of XSTest (Röttger et al. 2024, arXiv:2308.01263) intended for measuring over-refusal only...
evaluate
362
or-bench-1k-overrefusal 0 0
OR-Bench-1k (over-refusal subset) A manually-filtered subset of VityaVitalich/or-bench-1k, itself a 1000-prompt class-balanced subsample ...
evaluate
264
model-raising-pb-300k-3c-sft 0 0
jkminder/model-raising-pb-300k-3c-sft Charter-aware paired SFT dataset for the persona-binding bridge between charter-annotated pretraini...
evaluate
243
model-raising-pb-100k-3c-mt-sft 0 0
jkminder/model-raising-pb-100k-3c-mt-sft Multi-turn charter-aware paired SFT dataset for the persona-binding bridge between charter-annot...
evaluate
150
Dataset
Stage
Downloads
or-bench-1k-overrefusal 0 0
OR-Bench-1k (over-refusal subset) A manually-filtered subset of VityaVitalich/or-bench-1k, itself a 1000-prompt class-balanced subsample ...
evaluate
264
xstest-overrefusal 0 0
XSTest — Over-Refusal Subset A filtered subset of XSTest (Röttger et al. 2024, arXiv:2308.01263) intended for measuring over-refusal only...
evaluate
362
model-raising-pb-100k-3c-mt-sft 0 0
jkminder/model-raising-pb-100k-3c-mt-sft Multi-turn charter-aware paired SFT dataset for the persona-binding bridge between charter-annot...
evaluate
150
model-raising-pb-300k-3c-sft 0 0
jkminder/model-raising-pb-300k-3c-sft Charter-aware paired SFT dataset for the persona-binding bridge between charter-annotated pretraini...
evaluate
243
Dataset
Stage
Downloads
xstest-overrefusal 0 0
XSTest — Over-Refusal Subset A filtered subset of XSTest (Röttger et al. 2024, arXiv:2308.01263) intended for measuring over-refusal only...
evaluate
362
or-bench-1k-overrefusal 0 0
OR-Bench-1k (over-refusal subset) A manually-filtered subset of VityaVitalich/or-bench-1k, itself a 1000-prompt class-balanced subsample ...
evaluate
264
model-raising-pb-300k-3c-sft 0 0
jkminder/model-raising-pb-300k-3c-sft Charter-aware paired SFT dataset for the persona-binding bridge between charter-annotated pretraini...
evaluate
243
model-raising-pb-100k-3c-mt-sft 0 0
jkminder/model-raising-pb-100k-3c-mt-sft Multi-turn charter-aware paired SFT dataset for the persona-binding bridge between charter-annot...
evaluate
150
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