Alignment datasets by zjunlp

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
ChineseHarm-bench 0 0
ChineseHarm-bench A Chinese Harmful Content Detection Benchmark ⚠️ WARNING: This project and associated data contain content that may b...
5.2k
ConceptEdit 0 0
Editing Conceptual Knowledge for Large Language Models Overview • How To Use • Citation • Paper • Website ...
1.8k
Dataset
Stage
Downloads
ChineseHarm-bench 0 0
ChineseHarm-bench A Chinese Harmful Content Detection Benchmark ⚠️ WARNING: This project and associated data contain content that may b...
5.2k
ConceptEdit 0 0
Editing Conceptual Knowledge for Large Language Models Overview • How To Use • Citation • Paper • Website ...
1.8k
Dataset
Stage
Downloads
ChineseHarm-bench 0 0
ChineseHarm-bench A Chinese Harmful Content Detection Benchmark ⚠️ WARNING: This project and associated data contain content that may b...
5.2k
ConceptEdit 0 0
Editing Conceptual Knowledge for Large Language Models Overview • How To Use • Citation • Paper • Website ...
1.8k
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.

Open in Abliteration