huihui-ai/QwQ-32B-Preview-abliterated

huihui-ai/QwQ-32B-Preview-abliterated is an uncensored variant of the Qwen/QwQ-32B-Preview model. This model was created using an abliteration technique to remove refusal behaviors, serving as a proof-of-concept for uncensoring LLMs without TransformerLens. It is designed for applications requiring a less restrictive language model, particularly for exploring the effects of refusal removal.