Get the app
← back to catalog
AUTHOR

lmorlok

No models indexed under this account. Publishes 2 alignment datasets (721 downloads) tracked in our /datasets catalog.

Alignment datasets by lmorlok

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
hh-rlhf-llama-3-8b-embedding 0 0
Description This dataset contains the last-layer-embeddings of the hh-rlhf dataset. The model that we used for embedding is the llama-3-8...
extract
611
hh-rlhf-llama-3-70b-embedding 0 0
extract
110
Dataset
Stage
Downloads
hh-rlhf-llama-3-70b-embedding 0 0
extract
110
hh-rlhf-llama-3-8b-embedding 0 0
Description This dataset contains the last-layer-embeddings of the hh-rlhf dataset. The model that we used for embedding is the llama-3-8...
extract
611
Dataset
Stage
Downloads
hh-rlhf-llama-3-8b-embedding 0 0
Description This dataset contains the last-layer-embeddings of the hh-rlhf dataset. The model that we used for embedding is the llama-3-8...
extract
611
hh-rlhf-llama-3-70b-embedding 0 0
extract
110
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