license: cc-by-4.0
language:
- en
base_model:
- TeeZee/Orca-2-13b_flat
- NeverSleep/X-NoroChronos-13B
- NeverSleep/Noromaid-13b-v0.3
- KatyTheCutie/EstopianMaid-13B
- Undi95/MLewdBoros-L2-13B
- KoboldAI/LLaMA2-13B-Psyfighter2
- KoboldAI/LLaMA2-13B-Erebus-v3
library_name: transformers
tags:
- storywriting
- text adventure
- creative
- story
- writing
- fiction
- roleplaying
- rp
- mergekit
- merge
Bionic-Vaquita-13B
In the same vein as the legendary Psyonic-Cetacean-20B, I have attempted to create a 13B model that is equal parts creative and chaotic, while still remaining coherent enough for roleplaying purposes.
Seven different Llama-2 13B models were hand-picked and merged via TIES to create three separate components for the final stack (to be made public upon request).
Emotional intelligence and coherency were the primary focus of the late-stage manual testing that led to selecting this model.
This is a merge of pre-trained language models created using mergekit.
GGUF quants: https://huggingface.co/backyardai/Bionic-Vaquita-13B-GGUF
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
- FallenMerick/XNoroChronos-Orca2-Noromaid
- FallenMerick/Psyfighter2-Orca2-Erebus3
- FallenMerick/EstopianMaid-Orca2-MlewdBoros
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: FallenMerick/XNoroChronos-Orca2-Noromaid
layer_range: [0, 16]
- sources:
- model: FallenMerick/EstopianMaid-Orca2-MlewdBoros
layer_range: [16, 24]
- sources:
- model: FallenMerick/Psyfighter2-Orca2-Erebus3
layer_range: [24, 40]
merge_method: passthrough
dtype: bfloat16