Get the app
← back to catalog
AUTHOR

PKU-Alignment

No models indexed under this account. Publishes 2 alignment datasets (31.9k downloads) tracked in our /datasets catalog.

Alignment datasets by PKU-Alignment

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
processed-hh-rlhf 0 0
Dataset Card for Processed-Hh-RLHF This is a dataset that processes hh-rlhf into an easy-to-use conversational and human-preference form.
extract
24.5k
PKU-SafeRLHF-prompt 0 0
Dataset Card for PKU-SafeRLHF-prompt This dataset contains 44.6K unique prompts from PKU-SafeRLHF. 22.4% of the prompts in this dataset c...
fine-tune
7.4k
Dataset
Stage
Downloads
PKU-SafeRLHF-prompt 0 0
Dataset Card for PKU-SafeRLHF-prompt This dataset contains 44.6K unique prompts from PKU-SafeRLHF. 22.4% of the prompts in this dataset c...
fine-tune
7.4k
processed-hh-rlhf 0 0
Dataset Card for Processed-Hh-RLHF This is a dataset that processes hh-rlhf into an easy-to-use conversational and human-preference form.
extract
24.5k
Dataset
Stage
Downloads
processed-hh-rlhf 0 0
Dataset Card for Processed-Hh-RLHF This is a dataset that processes hh-rlhf into an easy-to-use conversational and human-preference form.
extract
24.5k
PKU-SafeRLHF-prompt 0 0
Dataset Card for PKU-SafeRLHF-prompt This dataset contains 44.6K unique prompts from PKU-SafeRLHF. 22.4% of the prompts in this dataset c...
fine-tune
7.4k
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.

Get the app Browse the catalog
Open in Abliteration