README.md

---
license: llama3.1
language:
- en
pipeline_tag: text-generation
base_model:
- allenai/Llama-3.1-Tulu-3-8B
library_name: transformers
tags:
- abliterated
- uncensored
---

# huihui-ai/Llama-3.1-Tulu-3-8B-abliterated


This is an uncensored version of [allenai/Llama-3.1-Tulu-3-8B](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B) 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.    

## ollama

You can use [huihui_ai/tulu3-abliterate](https://ollama.com/huihui_ai/tulu3-abliterate) directly, 
```
ollama run huihui_ai/tulu3-abliterate
```