Get the app
← back to catalog
AUTHOR

GoJulyAI

No models indexed under this account. Publishes 3 alignment datasets (680 downloads) tracked in our /datasets catalog.

Alignment datasets by GoJulyAI

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
illicit-general-multi-turn 0 0
Illicit General Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful illicit content from AI ...
extract
301
psychology-multi-turn 0 0
Psychology Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful psychological content from AI...
extract
208
illicit-bio-multi-turn 0 0
Illicit Bio Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful bio-safety content from AI m...
extract
171
Dataset
Stage
Downloads
illicit-general-multi-turn 0 0
Illicit General Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful illicit content from AI ...
extract
301
illicit-bio-multi-turn 0 0
Illicit Bio Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful bio-safety content from AI m...
extract
171
psychology-multi-turn 0 0
Psychology Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful psychological content from AI...
extract
208
Dataset
Stage
Downloads
illicit-general-multi-turn 0 0
Illicit General Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful illicit content from AI ...
extract
301
psychology-multi-turn 0 0
Psychology Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful psychological content from AI...
extract
208
illicit-bio-multi-turn 0 0
Illicit Bio Multi-Turn Conversations Multi-turn adversarial conversations that successfully elicited harmful bio-safety content from AI m...
extract
171
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