|
--- |
|
source_model: DavidAU/Psyonic-Cetacean-full-precision |
|
original_merge: jebcarter/psyonic-cetacean-20B |
|
language: |
|
- en |
|
library_name: transformers |
|
license: other |
|
license_name: microsoft-research-license |
|
quantized_by: Absurd |
|
tags: |
|
- storywriting |
|
- text adventure |
|
- not-for-all-audiences |
|
- creative |
|
- story |
|
- writing |
|
- fiction |
|
- float32 |
|
- roleplaying |
|
- rp |
|
- enhanced |
|
- space whale |
|
- 32 bit upscale |
|
--- |
|
# Psyonic-Cetacean-V1-20B-Ultra-Quality |
|
|
|
**Repo will be upgraded to h8 soon** |
|
|
|
6.9bpw (nice) h6 exl2 quant of https://huggingface.co/DavidAU/Psyonic-Cetacean-V1-20B-Ultra-Quality-Float32 |
|
|
|
Original merge model: https://huggingface.co/jebcarter/psyonic-cetacean-20B |
|
|
|
|
|
### This is a Llama2-based stack merge consisting of: |
|
|
|
- [KoboldAI/PsyFighter-2-13b](https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2-GGUF) |
|
- [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) |
|
|
|
Prompt format: Alpaca |
|
|
|
|
|
This model is focused on storywriting and text adventure, with a side order of Assistant and Chat functionality. Like its ancestor Psyfighter-2 this model will function better if you let it improvise and riff on your concepts rather than feeding it an excess of detail. |
|
Additionally, either the removal of the ChatML vocab or the stack merging process itself has resulted in not only an uncensored model but an actively anti-censored model, so please be aware that this model can and will kill you during adventures or output NSFW material if prompted accordingly. |
|
|
|
|
|
Thanks to https://huggingface.co/jebcarter for a wonderful model and https://huggingface.co/DavidAU for remastering it. |
|
|
