Get the app
← back to catalog
AUTHOR

submarat

No models indexed under this account. Publishes 1 alignment dataset (102 downloads) tracked in our /datasets catalog.

Alignment datasets by submarat

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
mats11-mix4-readout2x just added 0
Artifacts of sandbox/marat/2026-10-12-ge-mix4-readout2x of github.com/submarat/mats11-apollo-science-of-scheming: OLMo-3-1025-7B base, RL on...
evaluate
102
Dataset
Stage
Downloads
mats11-mix4-readout2x just added 0
Artifacts of sandbox/marat/2026-10-12-ge-mix4-readout2x of github.com/submarat/mats11-apollo-science-of-scheming: OLMo-3-1025-7B base, RL on...
evaluate
102
Dataset
Stage
Downloads
mats11-mix4-readout2x just added 0
Artifacts of sandbox/marat/2026-10-12-ge-mix4-readout2x of github.com/submarat/mats11-apollo-science-of-scheming: OLMo-3-1025-7B base, RL on...
evaluate
102
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