---
license: apache-2.0
language:
- en
- zh
base_model:
- Infinigence/Megrez-3B-Instruct
pipeline_tag: text-generation
tags:
- abliterated
- uncensored
library_name: transformers
---
# huihui-ai/Megrez-3B-Instruct-abliterated


This is an uncensored version of [Infinigence/Megrez-3B-Instruct](https://huggingface.co/Infinigence/Megrez-3B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/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/megrez-abliterated](https://ollama.com/huihui_ai/megrez-abliterated) directly
```
ollama run huihui_ai/megrez-abliterated
```