Get the app
← back to catalog
AUTHOR

piotreknow02

5 models in the catalog. 143 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 2 alignment datasets (500 downloads).

Alignment datasets by piotreknow02

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
harmful_behaviors_polish 0 0
harmful behaviors polish Dataset translated from mlabonne/harmful_behaviors to polish Statement on the Use of Harmful Prompt Data...
extract
401
harmless_alpaca_polish 0 0
extract
99
Dataset
Stage
Downloads
harmless_alpaca_polish 0 0
extract
99
harmful_behaviors_polish 0 0
harmful behaviors polish Dataset translated from mlabonne/harmful_behaviors to polish Statement on the Use of Harmful Prompt Data...
extract
401
Dataset
Stage
Downloads
harmful_behaviors_polish 0 0
harmful behaviors polish Dataset translated from mlabonne/harmful_behaviors to polish Statement on the Use of Harmful Prompt Data...
extract
401
harmless_alpaca_polish 0 0
extract
99
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