lenML/aya-expanse-8b-abliterated
5 files
↓ 264
♥ 10
AUTHOR
2 models in the catalog. 300 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 2 alignment datasets (1.5k 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
advbench_behaviors_m5 0 0
About advbench_behaviors_m5
此数据集为 advbench_behaviors.csv 文件的多语言翻译版本。一个常见的任务是用于 abliterator 脚本。
Dataset Card for AdvBench
Pape...
790
1
abliterate-refusal-cn 0 0
我使用本地模型将其翻译为中文，为了减少使用 "abliterator" 脚本时对llm中文能力的损害
Dataset for abliterating refusal in large language models
Contains "harmful" p...
730
-
Dataset
Stage
Downloads
Likes
advbench_behaviors_m5 0 0
About advbench_behaviors_m5
此数据集为 advbench_behaviors.csv 文件的多语言翻译版本。一个常见的任务是用于 abliterator 脚本。
Dataset Card for AdvBench
Pape...
790
1
abliterate-refusal-cn 0 0
我使用本地模型将其翻译为中文，为了减少使用 "abliterator" 脚本时对llm中文能力的损害
Dataset for abliterating refusal in large language models
Contains "harmful" p...
730
-
Dataset
Stage
Downloads
Likes
advbench_behaviors_m5 0 0
About advbench_behaviors_m5
此数据集为 advbench_behaviors.csv 文件的多语言翻译版本。一个常见的任务是用于 abliterator 脚本。
Dataset Card for AdvBench
Pape...
790
1
abliterate-refusal-cn 0 0
我使用本地模型将其翻译为中文，为了减少使用 "abliterator" 脚本时对llm中文能力的损害
Dataset for abliterating refusal in large language models
Contains "harmful" p...
730
-