Get the app
← back to catalog
AUTHOR

Seanie-lee

No models indexed under this account. Publishes 22 alignment datasets (3k downloads) tracked in our /datasets catalog.

Alignment datasets by Seanie-lee

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.

22 in /datasets
Dataset
Stage
Downloads
ThinkSafe-Qwen3-4B-WildGuard 0 0
ThinkSafe-Qwen3-4B-WildGuard Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning M...
evaluate
317
ThinkSafe-Qwen3-0.6B-WildGuard 0 0
THINKSAFE Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project. Datase...
evaluate
259
ThinkSafe-Qwen3-8B-WildGuard 0 0
ThinkSafe-Qwen3-8B-WildGuard Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project....
evaluate
228
ThinkSafe-Qwen3-1.7B-WildGuard 0 0
ThinkSafe Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning Models. Paper: https...
evaluate
221
ThinkSafe-4B-WildGuard 0 0
evaluate
179
ThinkSafe-R1-Distill-7B-WildGuard 0 0
evaluate
168
ThinkSafe-R1-Distill-8B-WildGuard 0 0
evaluate
138
ThinkSafe-8B-WildGuard 0 0
evaluate
125
ThinkSafe-8B-n4-filtered-qwen 0 0
Original dataset size: 159758 Total unique prompts: 39991 Harmful prompts: 17883 Benign prompts: 22108 Filtered dataset size: 39991 Harmf...
misc
119
ThinkSafe-R1-Distill-1.5B-WildGuard 0 0
evaluate
119
ThinkSafe-R1-Distill-7B-n4-filtered-qwen 0 0
Original dataset size: 157093 Total unique prompts: 39948 Harmful prompts: 17845 Benign prompts: 22103 Filtered dataset size: 39925 Harmf...
misc
114
ThinkSafe-R1-Distill-1.5B-n4-filtered-qwen 0 0
Original dataset size: 152942 Total unique prompts: 39828 Harmful prompts: 17753 Benign prompts: 22075 Filtered dataset size: 39402 Harmf...
misc
113
ThinkSafe-1.7B-WildGuard 0 0
evaluate
110
ThinkSafe-1.7B-n4-filtered-qwen 0 0
Original dataset size: 156447 Total unique prompts: 39765 Harmful prompts: 17667 Benign prompts: 22098 Filtered dataset size: 39617 Harmf...
misc
99
ThinkSafe-R1-Distill-1.5B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 1234Number of non-refusals: 16654Refusal rate: 6.90% Filtering Statisti...
evaluate
98
ThinkSafe-4B-n4-filtered-qwen 0 0
Original dataset size: 159612 Total unique prompts: 39989 Harmful prompts: 17882 Benign prompts: 22107 Filtered dataset size: 39986 Harmf...
misc
97
ThinkSafe-0.6B-WildGuard 0 0
evaluate
97
ThinkSafe-0.6B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 2722Number of non-refusals: 15166Refusal rate: 15.22% Filtering Statisti...
misc
96
ThinkSafe-R1-Distill-8B-n4-filtered-qwen 0 0
Original dataset size: 159163 Total unique prompts: 39990 Harmful prompts: 17883 Benign prompts: 22107 Filtered dataset size: 39988 Harmf...
misc
95
ThinkSafe-0.6B-n4-filtered-qwen 0 0
Original dataset size: 155881 Total unique prompts: 39760 Harmful prompts: 17672 Benign prompts: 22088 Filtered dataset size: 39609 Harmf...
misc
93
ThinkSafe-R1-Distill-8B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 4654Number of non-refusals: 13234Refusal rate: 26.02% Filtering Statis...
misc
84
ThinkSafe-R1-Distill-7B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 3785Number of non-refusals: 14103Refusal rate: 21.16% Filtering Statist...
misc
79
Dataset
Stage
Downloads
ThinkSafe-Qwen3-8B-WildGuard 0 0
ThinkSafe-Qwen3-8B-WildGuard Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project....
evaluate
228
ThinkSafe-Qwen3-4B-WildGuard 0 0
ThinkSafe-Qwen3-4B-WildGuard Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning M...
evaluate
317
ThinkSafe-Qwen3-1.7B-WildGuard 0 0
ThinkSafe Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning Models. Paper: https...
evaluate
221
ThinkSafe-Qwen3-0.6B-WildGuard 0 0
THINKSAFE Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project. Datase...
evaluate
259
ThinkSafe-R1-Distill-7B-WildGuard 0 0
evaluate
168
ThinkSafe-R1-Distill-1.5B-WildGuard 0 0
evaluate
119
ThinkSafe-8B-WildGuard 0 0
evaluate
125
ThinkSafe-4B-WildGuard 0 0
evaluate
179
ThinkSafe-R1-Distill-8B-WildGuard 0 0
evaluate
138
ThinkSafe-1.7B-WildGuard 0 0
evaluate
110
ThinkSafe-0.6B-WildGuard 0 0
evaluate
97
ThinkSafe-R1-Distill-1.5B-n4-filtered-qwen 0 0
Original dataset size: 152942 Total unique prompts: 39828 Harmful prompts: 17753 Benign prompts: 22075 Filtered dataset size: 39402 Harmf...
misc
113
ThinkSafe-R1-Distill-7B-n4-filtered-qwen 0 0
Original dataset size: 157093 Total unique prompts: 39948 Harmful prompts: 17845 Benign prompts: 22103 Filtered dataset size: 39925 Harmf...
misc
114
ThinkSafe-1.7B-n4-filtered-qwen 0 0
Original dataset size: 156447 Total unique prompts: 39765 Harmful prompts: 17667 Benign prompts: 22098 Filtered dataset size: 39617 Harmf...
misc
99
ThinkSafe-4B-n4-filtered-qwen 0 0
Original dataset size: 159612 Total unique prompts: 39989 Harmful prompts: 17882 Benign prompts: 22107 Filtered dataset size: 39986 Harmf...
misc
97
ThinkSafe-R1-Distill-8B-n4-filtered-qwen 0 0
Original dataset size: 159163 Total unique prompts: 39990 Harmful prompts: 17883 Benign prompts: 22107 Filtered dataset size: 39988 Harmf...
misc
95
ThinkSafe-0.6B-n4-filtered-qwen 0 0
Original dataset size: 155881 Total unique prompts: 39760 Harmful prompts: 17672 Benign prompts: 22088 Filtered dataset size: 39609 Harmf...
misc
93
ThinkSafe-8B-n4-filtered-qwen 0 0
Original dataset size: 159758 Total unique prompts: 39991 Harmful prompts: 17883 Benign prompts: 22108 Filtered dataset size: 39991 Harmf...
misc
119
ThinkSafe-0.6B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 2722Number of non-refusals: 15166Refusal rate: 15.22% Filtering Statisti...
misc
96
ThinkSafe-R1-Distill-8B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 4654Number of non-refusals: 13234Refusal rate: 26.02% Filtering Statis...
misc
84
ThinkSafe-R1-Distill-7B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 3785Number of non-refusals: 14103Refusal rate: 21.16% Filtering Statist...
misc
79
ThinkSafe-R1-Distill-1.5B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 1234Number of non-refusals: 16654Refusal rate: 6.90% Filtering Statisti...
evaluate
98
Dataset
Stage
Downloads
ThinkSafe-Qwen3-4B-WildGuard 0 0
ThinkSafe-Qwen3-4B-WildGuard Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning M...
evaluate
317
ThinkSafe-Qwen3-0.6B-WildGuard 0 0
THINKSAFE Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project. Datase...
evaluate
259
ThinkSafe-Qwen3-8B-WildGuard 0 0
ThinkSafe-Qwen3-8B-WildGuard Dataset This dataset is part of the THINKSAFE: Self-Generated Safety Alignment for Reasoning Models project....
evaluate
228
ThinkSafe-Qwen3-1.7B-WildGuard 0 0
ThinkSafe Dataset This dataset is associated with the paper THINKSAFE: Self-Generated Safety Alignment for Reasoning Models. Paper: https...
evaluate
221
ThinkSafe-4B-WildGuard 0 0
evaluate
179
ThinkSafe-R1-Distill-7B-WildGuard 0 0
evaluate
168
ThinkSafe-R1-Distill-8B-WildGuard 0 0
evaluate
138
ThinkSafe-8B-WildGuard 0 0
evaluate
125
ThinkSafe-8B-n4-filtered-qwen 0 0
Original dataset size: 159758 Total unique prompts: 39991 Harmful prompts: 17883 Benign prompts: 22108 Filtered dataset size: 39991 Harmf...
misc
119
ThinkSafe-R1-Distill-1.5B-WildGuard 0 0
evaluate
119
ThinkSafe-R1-Distill-7B-n4-filtered-qwen 0 0
Original dataset size: 157093 Total unique prompts: 39948 Harmful prompts: 17845 Benign prompts: 22103 Filtered dataset size: 39925 Harmf...
misc
114
ThinkSafe-R1-Distill-1.5B-n4-filtered-qwen 0 0
Original dataset size: 152942 Total unique prompts: 39828 Harmful prompts: 17753 Benign prompts: 22075 Filtered dataset size: 39402 Harmf...
misc
113
ThinkSafe-1.7B-WildGuard 0 0
evaluate
110
ThinkSafe-1.7B-n4-filtered-qwen 0 0
Original dataset size: 156447 Total unique prompts: 39765 Harmful prompts: 17667 Benign prompts: 22098 Filtered dataset size: 39617 Harmf...
misc
99
ThinkSafe-R1-Distill-1.5B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 1234Number of non-refusals: 16654Refusal rate: 6.90% Filtering Statisti...
evaluate
98
ThinkSafe-4B-n4-filtered-qwen 0 0
Original dataset size: 159612 Total unique prompts: 39989 Harmful prompts: 17882 Benign prompts: 22107 Filtered dataset size: 39986 Harmf...
misc
97
ThinkSafe-0.6B-WildGuard 0 0
evaluate
97
ThinkSafe-0.6B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 2722Number of non-refusals: 15166Refusal rate: 15.22% Filtering Statisti...
misc
96
ThinkSafe-R1-Distill-8B-n4-filtered-qwen 0 0
Original dataset size: 159163 Total unique prompts: 39990 Harmful prompts: 17883 Benign prompts: 22107 Filtered dataset size: 39988 Harmf...
misc
95
ThinkSafe-0.6B-n4-filtered-qwen 0 0
Original dataset size: 155881 Total unique prompts: 39760 Harmful prompts: 17672 Benign prompts: 22088 Filtered dataset size: 39609 Harmf...
misc
93
ThinkSafe-R1-Distill-8B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 4654Number of non-refusals: 13234Refusal rate: 26.02% Filtering Statis...
misc
84
ThinkSafe-R1-Distill-7B-v3 0 0
Refusal Statistics:Total harmful prompts: 17888Number of refusals: 3785Number of non-refusals: 14103Refusal rate: 21.16% Filtering Statist...
misc
79
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