cowWhySo/qwen3-4b-unslop-abliterated-lora
no files listed
↓ 0
♥ 0
AUTHOR
1 model in the catalog. 0 total downloads. First seen 2026-09-07, last activity 2026-09-07. Also publishes 2 alignment datasets (3.1k downloads).
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
pentest-redteam-steering 0 0
These prompts are all reject by Llama 3 for being "harmful" related to security and pentesting.
They can be used for steering models using: ...
2.8k
17
permission-command-corpus 0 0
Permission Command Corpus
Three views of a command-safety corpus, for local command-risk classification in
front of an LLM or a tool brid...
325
1
Dataset
Stage
Downloads
Likes
permission-command-corpus 0 0
Permission Command Corpus
Three views of a command-safety corpus, for local command-risk classification in
front of an LLM or a tool brid...
325
1
pentest-redteam-steering 0 0
These prompts are all reject by Llama 3 for being "harmful" related to security and pentesting.
They can be used for steering models using: ...
2.8k
17
Dataset
Stage
Downloads
Likes
pentest-redteam-steering 0 0
These prompts are all reject by Llama 3 for being "harmful" related to security and pentesting.
They can be used for steering models using: ...
2.8k
17
permission-command-corpus 0 0
Permission Command Corpus
Three views of a command-safety corpus, for local command-risk classification in
front of an LLM or a tool brid...
325
1