Get the app
← back to catalog
AUTHOR

ddidacus

No models indexed under this account. Publishes 2 alignment datasets (751 downloads) tracked in our /datasets catalog.

Alignment datasets by ddidacus

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
guard-glp-data 0 0
guard-glp-data A prompt-level binary safety dataset for training and evaluating LLM guardrails, with a focus on adversarial / jailbreak r...
extract
592
harmeval-gcg-llama3-1b 0 0
harmeval-gcg-llama3-1b HarmEval (SoftMINER-Group/HarmEval) augmented with adversarial suffixes generated via the Greedy Coordinate Gradie...
extract
159
Dataset
Stage
Downloads
guard-glp-data 0 0
guard-glp-data A prompt-level binary safety dataset for training and evaluating LLM guardrails, with a focus on adversarial / jailbreak r...
extract
592
harmeval-gcg-llama3-1b 0 0
harmeval-gcg-llama3-1b HarmEval (SoftMINER-Group/HarmEval) augmented with adversarial suffixes generated via the Greedy Coordinate Gradie...
extract
159
Dataset
Stage
Downloads
guard-glp-data 0 0
guard-glp-data A prompt-level binary safety dataset for training and evaluating LLM guardrails, with a focus on adversarial / jailbreak r...
extract
592
harmeval-gcg-llama3-1b 0 0
harmeval-gcg-llama3-1b HarmEval (SoftMINER-Group/HarmEval) augmented with adversarial suffixes generated via the Greedy Coordinate Gradie...
extract
159
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