Alignment datasets by declare-lab

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
HarmfulQA 0 0
Paper | Github | Dataset| Model πŸ“£πŸ“£πŸ“£: Do check our new multilingual dataset CatQA here used in Safety Vectors:πŸ“£πŸ“£πŸ“£ As a part of our re...
30.9k
CategoricalHarmfulQA 0 0
CatQA: A categorical harmful questions dataset CatQA is used in LLM safety realignment research: Language Models are Homer Simpson! Saf...
10.4k
Dataset
Stage
Downloads
CategoricalHarmfulQA 0 0
CatQA: A categorical harmful questions dataset CatQA is used in LLM safety realignment research: Language Models are Homer Simpson! Saf...
10.4k
HarmfulQA 0 0
Paper | Github | Dataset| Model πŸ“£πŸ“£πŸ“£: Do check our new multilingual dataset CatQA here used in Safety Vectors:πŸ“£πŸ“£πŸ“£ As a part of our re...
30.9k
Dataset
Stage
Downloads
HarmfulQA 0 0
Paper | Github | Dataset| Model πŸ“£πŸ“£πŸ“£: Do check our new multilingual dataset CatQA here used in Safety Vectors:πŸ“£πŸ“£πŸ“£ As a part of our re...
30.9k
CategoricalHarmfulQA 0 0
CatQA: A categorical harmful questions dataset CatQA is used in LLM safety realignment research: Language Models are Homer Simpson! Saf...
10.4k
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