Get the app
← back to catalog
AUTHOR

Micdejc

No models indexed under this account. Publishes 2 alignment datasets (344 downloads) tracked in our /datasets catalog.

Alignment datasets by Micdejc

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
cymultenset 0 0
CyMulTenSet: Grammatical Mirage Attack Associated Paper: Jailbreaking LLMs Through Tense Manipulation in Multi-Turn Dialogues ...
evaluate
222
refusalguard-m 0 0
RefusalGuard-M Dataset This repository contains the datasets associated with the RefusalGuard-M framework for multi-turn LLM jailbreak ev...
extract
122
Dataset
Stage
Downloads
refusalguard-m 0 0
RefusalGuard-M Dataset This repository contains the datasets associated with the RefusalGuard-M framework for multi-turn LLM jailbreak ev...
extract
122
cymultenset 0 0
CyMulTenSet: Grammatical Mirage Attack Associated Paper: Jailbreaking LLMs Through Tense Manipulation in Multi-Turn Dialogues ...
evaluate
222
Dataset
Stage
Downloads
cymultenset 0 0
CyMulTenSet: Grammatical Mirage Attack Associated Paper: Jailbreaking LLMs Through Tense Manipulation in Multi-Turn Dialogues ...
evaluate
222
refusalguard-m 0 0
RefusalGuard-M Dataset This repository contains the datasets associated with the RefusalGuard-M framework for multi-turn LLM jailbreak ev...
extract
122
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