exl2 8.0 quant

lumikabra-123B

This is lumikabra. It's based on Mistral-Large-Instruct-2407 , merged with Magnum-v2-123B, Luminum-v0.1-123B and Tess-3-Mistral-Large-2-123B.

I shamelessly took this idea from FluffyKaeloky. Like him, i always had my troubles with each of the current large mistral based models. Either it gets repetitive, shows too many GPTisms, is too horny or too unhorny. RP and storytelling is always a matter of taste, and i found myself swiping too often for new answers or even fixing them when I missed a little spice or cleverness.

Luminum was a great improvement, mixing a lot of desired traits, but I still missed some spice, another sauce. So i took Luminum, added magnum again and also Tess for knowledge and structure.

This is my very first merge, but I feel it has some potential. I was honestly a little surprised when my character was killed in RP just because it kinda fitted the story. So I guess, dark is a possible theme.

Merge Details

Merge Method

This model was merged using mergekit with the della_linear merge method using mistralai_Mistral-Large-Instruct-2407 as a base.

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org_magnum-v2-123b
    parameters:
      weight: 0.19
      density: 0.5
  - model: FluffyKaeloky_Luminum-v0.1-123B
    parameters:
      weight: 0.34
      density: 0.8
  - model: migtissera_Tess-3-Mistral-Large-2-123B
    parameters:
      weight: 0.24
      density: 0.7      
merge_method: della_linear
base_model: mistralai_Mistral-Large-Instruct-2407
parameters:
  epsilon: 0.05
  lambda: 1
  int8_mask: true
dtype: bfloat16