huihui-ai/aya-expanse-32b-abliterated

This is an uncensored version of CohereForAI/aya-expanse-32b created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

Use with ollama

You can use huihui_ai/aya-expanse-abliterated directly,

ollama run huihui_ai/aya-expanse-abliterated:32b