---
base_model:
- Undi95/Llama-3-Unholy-8B
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Aura_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/RP_Format_QuoteAsterisk_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Luna_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/Theory_of_Mind_Llama3
- Undi95/Llama-3-Unholy-8B
- ResplendentAI/BlueMoon_Llama3
license: apache-2.0
tags:
- roleplay
- llama3
- sillytavern
language:
- en
---

> [!CAUTION]
> **Outdated:** <br>
> Outdaded tokenizer configuration! <br>
> This is only kept for historical purposes, use the newer models instead of this one.

**This is a Llama-3 land now, cowboys!**

This is another *better* atempt at a less censored Llama-3 with hopefully more stable formatting.

GGUF-IQ-Imatrix quants for [ResplendentAI/Aura_Uncensored_l3_8B](https://huggingface.co/ResplendentAI/Aura_Uncensored_l3_8B).

> [!WARNING]
> Recommended presets [here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/cope-llama-3-0.1) or [here](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
> Use the latest version of KoboldCpp. **Use the provided presets.** <br>
> This is all still highly experimental, modified configs were used to avoid the tokenizer issues, let the authors know how it performs for you, feedback is more important than ever now.

**Original model information:**

# Aura Uncensored l3

![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/oiYHWIEHqmgUkY0GsVdDx.png)

This is the culmination of all my efforts for the Aura line. I have taken the original training data and applied it over Undi95's Unholy base model. This model can and will provide unsafe information and RP. I strongly recommend that you do not use this model if you are sensitive to unsafe output. 

I have tested the model thoroughly and believe that it will please the majority of users. I hope that you enjoy this model.