huihui-ai/Huihui-Jan-nano-128k-abliterated

Huihui-ai/Huihui-Jan-nano-128k-abliterated is a 4 billion parameter uncensored language model derived from Menlo/Jan-nano-128k, featuring a 40960 token context length. This model was created using an abliteration technique to remove refusal behaviors, serving as a proof-of-concept for uncensored LLM development without TransformerLens. It is primarily intended for research and experimental use in scenarios requiring reduced safety filtering.