Get the app
← back to catalog
AUTHOR

zdxnlp

No models indexed under this account. Publishes 2 alignment datasets (437 downloads) tracked in our /datasets catalog.

Alignment datasets by zdxnlp

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
JailJudge 0 0
Overview Although significant research efforts have been dedicated to enhancing the safety of large language models (LLMs) by understandi...
extract
277
SaladBench 0 0
Dataset Card for SaladBench Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models Data: SafeTex...
evaluate
160
Dataset
Stage
Downloads
SaladBench 0 0
Dataset Card for SaladBench Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models Data: SafeTex...
evaluate
160
JailJudge 0 0
Overview Although significant research efforts have been dedicated to enhancing the safety of large language models (LLMs) by understandi...
extract
277
Dataset
Stage
Downloads
JailJudge 0 0
Overview Although significant research efforts have been dedicated to enhancing the safety of large language models (LLMs) by understandi...
extract
277
SaladBench 0 0
Dataset Card for SaladBench Paper: SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models Data: SafeTex...
evaluate
160
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