license: apache-2.0
language:
- en
tags:
- roleplay
- sillytavern
- unaligned
- llama
GGUF-Imatrix quants for jeiku/Orthocopter_8B as per demand for testing.
This is experimental.
My upload speeds have been cooked and unstable lately.
If you want and you are able to...
You can support my various endeavors here (Ko-fi).
Compatible SillyTavern presets here (simple) or here (Virt's Roleplay Presets - recommended).
Use the latest version of KoboldCpp. Use the provided presets for testing.
Original model information from author card:
Orthocopter
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.