Bahushruth/abliteration-harmful-enriched download history
Bahushruth/abliteration-harmful-enriched is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 169 times (44 in the last 7 days), and 1,410 times in total. It ranks #101,550 among datasets by monthly downloads.
abliteration-harmful-enriched Enriched harmful prompt dataset for abliteration (refusal direction identification). 7356 prompts across 33 categories, designed to provide broad coverage of the refusal subspace for more accurate direction estimation. Used to produce: Bahushruth/Qwen3.6
Models trained on abliteration-harmful-enriched
10 models list it as training data.
- Bahushruth/Qwen3.6-35B-A3B-abliterated-v4 296.7K downloads in 30 days
- prem-research/DeepSeek-V4-Flash-0731-abliterated 259K downloads in 30 days
- Bahushruth/Qwen3.6-35B-A3B-abliterated-v4-GGUF 18.7K downloads in 30 days
- UnderTides/DeepSeek-V4.1-Flash-1017-heretic-lora 127 downloads in 30 days
- Bahushruth/gemma-4-E4B-it-abliterated 76 downloads in 30 days
- Bahushruth/gemma-4-26B-A4B-it-abliterated 36 downloads in 30 days
- Bahushruth/gemma-4-31B-it-abliterated 23 downloads in 30 days
- Bahushruth/gemma-4-E2B-it-abliterated 20 downloads in 30 days
- Bahushruth/GLM-5.2-FP8-abliterated 10 downloads in 30 days
- Ahadkarim/Agent47 0 downloads in 30 days
Open Bahushruth/abliteration-harmful-enriched on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.