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. 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