---
license: apache-2.0
language:
- en
tags:
- roleplay
- sillytavern
- unaligned
- llama
---
GGUF-Imatrix quants for [**jeiku/Orthocopter_8B**](https://huggingface.co/jeiku/Orthocopter_8B) as per demand for testing.

**This is experimental.**

<!-- > [!IMPORTANT]
> Based on the latest **llama.cpp** with the new conversion fixes hopefully already completed.
-->

> [!TIP]
> My upload speeds have been cooked and unstable lately. <br>
> If you **want** and you are able to... <br>
> You can [**support my various endeavors here (Ko-fi)**](https://ko-fi.com/Lewdiculous).

> [!NOTE]
> Compatible SillyTavern presets [**here (simple)**](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B/tree/main/Official%20Poppy%20Porpoise%20ST%20Presets) or [**here (Virt's Roleplay Presets - recommended)**](https://huggingface.co/Virt-io/SillyTavern-Presets). <br>
> Use the latest version of KoboldCpp. **Use the provided presets for testing.**

**Original model information from author card:**

# Orthocopter

![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/cxM5EaC6ilXnSo_10stA8.png)

This model is thanks to the hard work of lucyknada with the Edgerunners. Her work produced the following model, which I used as the base:

https://huggingface.co/Edgerunners/meta-llama-3-8b-instruct-hf-ortho-baukit-10fail-1000total

I then applied two handwritten datasets over top of this and the results are pretty nice, with no refusals and plenty of personality.