Get the app
← back to catalog
AUTHOR

hlyn-labs

No models indexed under this account. Publishes 3 alignment datasets (2.7k downloads) tracked in our /datasets catalog.

Alignment datasets by hlyn-labs

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.

3 in /datasets
Dataset
Stage
Downloads
prompt-injection-judge-deberta-dataset 0 0
🛡️ Prompt Injection Detection Dataset A 400K-sample, production-grade dataset for training binary classifiers to detect prompt injection...
extract
1.4k
prompt-injection-judge-dataset-v2 0 0
Prompt Injection Judge Dataset - Version 2 🛡️ Dataset Description The Prompt Injection Judge Dataset (V2) is a preference...
extract
686
prompt-injection-judge-dataset-v1 0 0
Defender Stage 2 Judge Fine-Tuning Dataset (SOTA Calibration) This dataset is designed to fine-tune an uncensored base model (like dphn/D...
fine-tune
570
Dataset
Stage
Downloads
prompt-injection-judge-deberta-dataset 0 0
🛡️ Prompt Injection Detection Dataset A 400K-sample, production-grade dataset for training binary classifiers to detect prompt injection...
extract
1.4k
prompt-injection-judge-dataset-v2 0 0
Prompt Injection Judge Dataset - Version 2 🛡️ Dataset Description The Prompt Injection Judge Dataset (V2) is a preference...
extract
686
prompt-injection-judge-dataset-v1 0 0
Defender Stage 2 Judge Fine-Tuning Dataset (SOTA Calibration) This dataset is designed to fine-tune an uncensored base model (like dphn/D...
fine-tune
570
Dataset
Stage
Downloads
prompt-injection-judge-deberta-dataset 0 0
🛡️ Prompt Injection Detection Dataset A 400K-sample, production-grade dataset for training binary classifiers to detect prompt injection...
extract
1.4k
prompt-injection-judge-dataset-v2 0 0
Prompt Injection Judge Dataset - Version 2 🛡️ Dataset Description The Prompt Injection Judge Dataset (V2) is a preference...
extract
686
prompt-injection-judge-dataset-v1 0 0
Defender Stage 2 Judge Fine-Tuning Dataset (SOTA Calibration) This dataset is designed to fine-tune an uncensored base model (like dphn/D...
fine-tune
570
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