Get the app
← back to catalog
AUTHOR

Alookhoshk

No models indexed under this account. Publishes 1 alignment dataset (214 downloads) tracked in our /datasets catalog.

Alignment datasets by Alookhoshk

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.

1 in /datasets
Dataset
Stage
Downloads
llama2-high-entropy-prompts 0 0
High-entropy prompts for suffix-based backdoor detection Prompts on which base meta-llama/Llama-2-7b-hf has high predictive entropy, buil...
misc
214
Dataset
Stage
Downloads
llama2-high-entropy-prompts 0 0
High-entropy prompts for suffix-based backdoor detection Prompts on which base meta-llama/Llama-2-7b-hf has high predictive entropy, buil...
misc
214
Dataset
Stage
Downloads
llama2-high-entropy-prompts 0 0
High-entropy prompts for suffix-based backdoor detection Prompts on which base meta-llama/Llama-2-7b-hf has high predictive entropy, buil...
misc
214
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