Get the app
← back to catalog
AUTHOR

NousResearch

No models indexed under this account. Publishes 2 alignment datasets (3.6k downloads) tracked in our /datasets catalog.

Alignment datasets by NousResearch

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
eval-Hermes-4.3-36B-centralized 0 0
36btorchtitan Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.706 math_pass@1:...
evaluate
2.1k
eval-Hermes-4.3-36B 0 0
36bpsychev2 Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.719 math_pass@1:64...
evaluate
1.5k
Dataset
Stage
Downloads
eval-Hermes-4.3-36B-centralized 0 0
36btorchtitan Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.706 math_pass@1:...
evaluate
2.1k
eval-Hermes-4.3-36B 0 0
36bpsychev2 Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.719 math_pass@1:64...
evaluate
1.5k
Dataset
Stage
Downloads
eval-Hermes-4.3-36B 0 0
36bpsychev2 Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.719 math_pass@1:64...
evaluate
1.5k
eval-Hermes-4.3-36B-centralized 0 0
36btorchtitan Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.706 math_pass@1:...
evaluate
2.1k
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