AlexWortega/qwen3.5-4b-abliterated-agent-20260515
no files listed
↓ 87
♥ 0
AUTHOR
6 models in the catalog. 149 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 2 alignment datasets (260 downloads).
AlexWortega/qwen35-4b-soyuz-abliterated-v3-multi
1 files
trained on 1 dataset
↓ 16
♥ 0
AlexWortega/qwen35-4b-soyuz-abliterated-v8_cfact
1 files
trained on 1 dataset
↓ 15
♥ 0
AlexWortega/qwen35-4b-soyuz-abliterated-v2
1 files
trained on 1 dataset
↓ 11
♥ 0
AlexWortega/qwen35-4b-soyuz-abliterated-v6_hardpairs
1 files
trained on 1 dataset
↓ 11
♥ 0
AlexWortega/qwen35-4b-soyuz-abliterated-v7_agentonly
1 files
trained on 1 dataset
↓ 9
♥ 0
Alignment datasets by
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.
Dataset
Stage
Downloads
Likes
capability-vectors 0 0
capability-vectors — PASS / FAIL contrast trajectories
This dataset bundles the exact PASS (comply) and FAIL (refuse) trajectories used t...
209
-
Dataset
Stage
Downloads
Likes
capability-vectors 0 0
capability-vectors — PASS / FAIL contrast trajectories
This dataset bundles the exact PASS (comply) and FAIL (refuse) trajectories used t...
209
-
Dataset
Stage
Downloads
Likes
capability-vectors 0 0
capability-vectors — PASS / FAIL contrast trajectories
This dataset bundles the exact PASS (comply) and FAIL (refuse) trajectories used t...
209
-