datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2
Dataset Card for Evaluation run of zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
Dataset automatically created during the evaluation run of model zetasepic/Qwen2.5-32B-Instruct-abliterated-v2.
The dataset is composed of 116 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_zetasepic__Qwen2.5-32B-Instruct-abliterated-v2_v2.details_v000000__SwallowMaid-8B-L3-SPPO-abliterated
Dataset Card for Evaluation run of v000000/SwallowMaid-8B-L3-SPPO-abliterated
Dataset automatically created during the evaluation run of model v000000/SwallowMaid-8B-L3-SPPO-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_v000000__SwallowMaid-8B-L3-SPPO-abliterated.details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated
Dataset Card for Evaluation run of Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated
Dataset automatically created during the evaluation run of model Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated.details_huihui-ai__Qwen2.5-7B-Instruct-abliterated
Dataset Card for Evaluation run of huihui-ai/Qwen2.5-7B-Instruct-abliterated
Dataset automatically created during the evaluation run of model huihui-ai/Qwen2.5-7B-Instruct-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_huihui-ai__Qwen2.5-7B-Instruct-abliterated.details_huihui-ai__DeepSeek-R1-Distill-Qwen-32B-abliterated
Dataset Card for Evaluation run of huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
Dataset automatically created during the evaluation run of model huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_huihui-ai__DeepSeek-R1-Distill-Qwen-32B-abliterated.details_byroneverson__Yi-1.5-9B-Chat-16K-abliterated
Dataset Card for Evaluation run of byroneverson/Yi-1.5-9B-Chat-16K-abliterated
Dataset automatically created during the evaluation run of model byroneverson/Yi-1.5-9B-Chat-16K-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_byroneverson__Yi-1.5-9B-Chat-16K-abliterated.details_byroneverson__Yi-1.5-9B-Chat-abliterated
Dataset Card for Evaluation run of byroneverson/Yi-1.5-9B-Chat-abliterated
Dataset automatically created during the evaluation run of model byroneverson/Yi-1.5-9B-Chat-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_byroneverson__Yi-1.5-9B-Chat-abliterated.details_informatiker__Qwen2-7B-Instruct-abliterated
Dataset Card for Evaluation run of informatiker/Qwen2-7B-Instruct-abliterated
Dataset automatically created during the evaluation run of model informatiker/Qwen2-7B-Instruct-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_informatiker__Qwen2-7B-Instruct-abliterated.details_mlabonne__NeuralDaredevil-8B-abliterated
Dataset Card for Evaluation run of mlabonne/NeuralDaredevil-8B-abliterated
Dataset automatically created during the evaluation run of model mlabonne/NeuralDaredevil-8B-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_mlabonne__NeuralDaredevil-8B-abliterated.CombinHorizon__huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES-details
Dataset Card for Evaluation run of CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES
Dataset automatically created during the evaluation run of model CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/CombinHorizon__huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES-details.zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details
Dataset Card for Evaluation run of zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
Dataset automatically created during the evaluation run of model zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/zetasepic__Qwen2.5-32B-Instruct-abliterated-v2-details.failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5-details
Dataset Card for Evaluation run of failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
Dataset automatically created during the evaluation run of model failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5-details.netcat420__MFANN-llama3.1-abliterated-SLERP-v3-details
Dataset Card for Evaluation run of netcat420/MFANN-llama3.1-abliterated-SLERP-v3
Dataset automatically created during the evaluation run of model netcat420/MFANN-llama3.1-abliterated-SLERP-v3
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/netcat420__MFANN-llama3.1-abliterated-SLERP-v3-details.huihui-ai__Qwen2.5-72B-Instruct-abliterated-details
Dataset Card for Evaluation run of huihui-ai/Qwen2.5-72B-Instruct-abliterated
Dataset automatically created during the evaluation run of model huihui-ai/Qwen2.5-72B-Instruct-abliterated
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/huihui-ai__Qwen2.5-72B-Instruct-abliterated-details.abliterated-distill-15kIsaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-details
Dataset Card for Evaluation run of Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated
Dataset automatically created during the evaluation run of model Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-details.Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details
Dataset Card for Evaluation run of Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Dataset automatically created during the evaluation run of model Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Goekdeniz-Guelmez__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details.zetasepic__Qwen2.5-72B-Instruct-abliterated-details
Dataset Card for Evaluation run of zetasepic/Qwen2.5-72B-Instruct-abliterated
Dataset automatically created during the evaluation run of model zetasepic/Qwen2.5-72B-Instruct-abliterated
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/zetasepic__Qwen2.5-72B-Instruct-abliterated-details.nbeerbower__EVA-abliterated-TIES-Qwen2.5-14B-details
Dataset Card for Evaluation run of nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B
Dataset automatically created during the evaluation run of model nbeerbower/EVA-abliterated-TIES-Qwen2.5-14B
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/nbeerbower__EVA-abliterated-TIES-Qwen2.5-14B-details.DavidAU__Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-details
Dataset Card for Evaluation run of DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B
Dataset automatically created during the evaluation run of model DavidAU/Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DavidAU__Qwen2.5-MOE-2X7B-DeepSeek-Abliterated-Censored-19B-details.Triangle104__Phi-4-AbliteratedRP-details
Dataset Card for Evaluation run of Triangle104/Phi-4-AbliteratedRP
Dataset automatically created during the evaluation run of model Triangle104/Phi-4-AbliteratedRP
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Triangle104__Phi-4-AbliteratedRP-details.qwen38-27B-abliterated-refusal-eval-fr
Qwen3.8-27B abliterated — French refusal eval
Bilingual evaluation set for measuring refusal vs compliance after abliteration.
This is not an instruction-tuning / uncensor SFT corpus. Assistant how-to completions from the source dataset are omitted.
Contents
Column
Description
id
Stable row id
user_en
Original English user prompt
user_fr
French translation (GX10 qwen-coder, translate-only)
user_safe / user_category
Qwen3Guard-style labels from the… See the full description on the dataset page: https://huggingface.co/datasets/GoldfingerCH/qwen38-27B-abliterated-refusal-eval-fr.Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details
Dataset Card for Evaluation run of Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
Dataset automatically created during the evaluation run of model Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Isaak-Carter__Josiefied-Qwen2.5-7B-Instruct-abliterated-v2-details.details_mlabonne__Daredevil-8B-abliterated
Dataset Card for Evaluation run of mlabonne/Daredevil-8B-abliterated
Dataset automatically created during the evaluation run of model mlabonne/Daredevil-8B-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_mlabonne__Daredevil-8B-abliterated.mlabonne__NeuralDaredevil-8B-abliterated-details
Dataset Card for Evaluation run of mlabonne/NeuralDaredevil-8B-abliterated
Dataset automatically created during the evaluation run of model mlabonne/NeuralDaredevil-8B-abliterated
The dataset is composed of 39 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 5 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/mlabonne__NeuralDaredevil-8B-abliterated-details.details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated
Dataset Card for Evaluation run of mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
Dataset automatically created during the evaluation run of model mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_mlabonne__Meta-Llama-3.1-8B-Instruct-abliterated.details_huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2
Dataset Card for Evaluation run of huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
Dataset automatically created during the evaluation run of model huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_huihui-ai__Qwen2.5-7B-Instruct-abliterated-v2.details_failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5
Dataset Card for Evaluation run of failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5
Dataset automatically created during the evaluation run of model failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_failspy__Meta-Llama-3-70B-Instruct-abliterated-v3.5.byroneverson__Yi-1.5-9B-Chat-16K-abliterateddetails_cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated
Dataset Card for Evaluation run of cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
Dataset automatically created during the evaluation run of model cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated.
The dataset is composed of 136 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_cognitivecomputations__dolphin-2.9.2-Phi-3-Medium-abliterated.