README.md

metadata

license: apache-2.0
language:
  - en
base_model:
  - qingy2024/UwU-7B-Instruct
pipeline_tag: text-generation
tags:
  - abliterated
  - uncensored
library_name: transformers

huihui-ai/UwU-7B-Instruct-abliterated

This is an uncensored version of qingy2024/UwU-7B-Instruct 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/uwu-abliterated directly

ollama run huihui_ai/uwu-abliterated