merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using unsloth/Mistral-Small-Instruct-2409 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  # Primary Fiction Core (Increased weights for core fiction models)
  - model: Kaoeiri/MS_Moingooistral-2409-22B  # Monster fiction core
    parameters:
      weight: 0.35  # Increased from 0.23
      density: 1.25 # Slightly increased for richer output
  
  - model: Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2-Cydonia-vXXX-22B-5  # Main writing engine
    parameters:
      weight: 0.95  # Increased from 0.85
      density: 0.82 # Increased for better coherence
  
  # World Building & Fantasy (Enhanced for richer fictional worlds)
  - model: Kaoeiri/MS-Inky-2409-22B  # Descriptive world dynamics
    parameters:
      weight: 0.40  # Increased significantly
      density: 0.78
  
  - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small  # Rich interaction
    parameters:
      weight: 0.38  # Increased for better character interaction
      density: 0.76
  
  # Character & Monster Development
  - model: DigitalSouls/BlackSheep-DigitalSoul-22B  # Combat and conflict
    parameters:
      weight: 0.25  # Moderate increase
      density: 0.72
  
  - model: InferenceIllusionist/SorcererLM-22B  # Magical elements
    parameters:
      weight: 0.28  # Increased for more magical elements
      density: 0.74
  
  # Reduced weights for secondary features
  - model: TheDrummer/Cydonia-22B-v1.1
    parameters:
      weight: 0.12
      density: 0.65
  
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.15
      density: 0.70
  
  - model: Kaoeiri/MS_a-coolyte-2409-22B
    parameters:
      weight: 0.18
      density: 0.69
  
  - model: Kaoeiri/MS_fujin-2409-22B
    parameters:
      weight: 0.14
      density: 0.68
  
  - model: Kaoeiri/MS-Quadrosiac-2409-22B
    parameters:
      weight: 0.15
      density: 0.71
  
  - model: Kaoeiri/MS_dampf-2409-22B
    parameters:
      weight: 0.15
      density: 0.71
  
  # Story Enhancement (Maintained moderate weights)
  - model: hf-100/Mistral-Small-Spellbound-StoryWriter-22B-instruct-0.2-chkpt-200-16-bit
    parameters:
      weight: 0.20
      density: 0.70
  
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.10
      density: 0.63
  
  - model: Darkknight535/MS-Moonlight-22B-v3
    parameters:
      weight: 0.10
      density: 0.63
  
  # Reduced weight for community tuning
  - model: Jellywibble/MistralSmall1500CTXDummy
    parameters:
      weight: 0.02
      density: 0.60
  
  # Cultural and Character elements (Maintained for depth)
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
    parameters:
      weight: 0.18
      density: 0.58
  
  - model: Envoid/Mistral-Small-NovusKyver
    parameters:
      weight: 0.25
      density: 0.71
  
  - model: TroyDoesAI/BlackSheep-MermaidMistral-22B
    parameters:
      weight: 0.22
      density: 0.70

merge_method: dare_ties
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.92    # Increased for even richer fictional detail
  epsilon: 0.04    # Further reduced for more consistent style
  lambda: 1.45     # Increased to enhance creative elements
dtype: bfloat16
tokenizer_source: union

Kaoeiri
/

MS-MagpantheonselRP-22B-12.22-Fictional

merge

Merge Details

Merge Method

Models Merged

Configuration

Model tree for Kaoeiri/MS-MagpantheonselRP-22B-12.22-Fictional