Model Card for Model ID
Qwen2.5-3B-Instruct-Abliterated
Model Sources [optional]
- Qwen2.5-3B-Instruct: [https://huggingface.co/Qwen/Qwen2.5-3B-Instruct]
- FailSpy: [https://github.com/FailSpy/abliterator]
- Refusal in LLMs is mediated by a single direction: [https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction]
- Uncensor any LLM with abliteration: [https://huggingface.co/blog/mlabonne/abliteration]
Uses
有限资VRAM资源的场景使用NSFW RolePlay或其他需要Uncensored模型的场景
- Downloads last month
- 17