Kaoeiri/MS-MagpantheonselRP-22B-11.1

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:

• Kaoeiri/MS_fujin-2409-22B
• InferenceIllusionist/SorcererLM-22B
• Darkknight535/MS-Moonlight-22B-v3
• crestf411/MS-sunfall-v0.7.0
• Kaoeiri/MS_springydragon-2409-22B
• hf-100/Mistral-Small-Spellbound-StoryWriter-22B-instruct-0.2-chkpt-200-16-bit
• Kaoeiri/MS_a-coolyte-2409-22B
• Kaoeiri/MS_Moingooistral-2409-22B
• Kaoeiri/MS_dampf-2409-22B
• Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
• Kaoeiri/MS-Physician-2409-22B
• ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
• Kaoeiri/Magnum-v4-Cydonia-vXXX-22B
• Gryphe/Pantheon-RP-1.6.2-22b-Small
• DigitalSouls/BlackSheep-DigitalSoul-22B
• allura-org/MS-Meadowlark-22B
• spow12/ChatWaifu_v2.0_22B
• Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
• anthracite-org/magnum-v4-22b

Configuration

The following YAML configuration was used to produce this model:

models:
  # Primary RP and Interaction Models
  - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
    parameters:
      weight: 0.26
      density: 0.74
  - model: Kaoeiri/MS_Moingooistral-2409-22B
    parameters:
      weight: 0.23
      density: 0.75

  # Versatile, High-Performance Models
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 1.0
      density: 0.86
  - model: DigitalSouls/BlackSheep-DigitalSoul-22B
    parameters:
      weight: 0.18
      density: 0.68
  - model: InferenceIllusionist/SorcererLM-22B
    parameters:
      weight: 0.19
      density: 0.70
  - model: Kaoeiri/Magnum-v4-Cydonia-vXXX-22B
    parameters:
      weight: 0.22
      density: 0.68
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.21
      density: 0.70

  # Supporting and Adapter-Based Models
  - model: Kaoeiri/MS_a-coolyte-2409-22B
    parameters:
      weight: 0.22
      density: 0.69
  - model: Kaoeiri/MS_fujin-2409-22B
    parameters:
      weight: 0.16
      density: 0.68
  - model: Kaoeiri/MS_springydragon-2409-22B
    parameters:
      weight: 0.17
      density: 0.71
  - model: Kaoeiri/MS_dampf-2409-22B
    parameters:
      weight: 0.17
      density: 0.71
  - model: Kaoeiri/MS-Physician-2409-22B
    parameters:
      weight: 0.10
      density: 0.67
  - model: hf-100/Mistral-Small-Spellbound-StoryWriter-22B-instruct-0.2-chkpt-200-16-bit
    parameters:
      weight: 0.18
      density: 0.67

  # Secondary and Low-Priority RP Models
  - model: Gryphe/Pantheon-RP-1.6.2-22b-Small
    parameters:
      weight: 0.13
      density: 0.65
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.12
      density: 0.63
  - model: Darkknight535/MS-Moonlight-22B-v3
    parameters:
      weight: 0.11
      density: 0.63

  # Additional Models
  - model: spow12/ChatWaifu_v2.0_22B
    parameters:
      weight: 0.27
      density: 0.7
  - model: Saxo/Linkbricks-Horizon-AI-Japanese-Superb-V1-22B
    parameters:
      weight: 0.2
      density: 0.58
  - model: allura-org/MS-Meadowlark-22B
    parameters:
      weight: 0.27
      density: 0.71

merge_method: dare_ties
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.85
  epsilon: 0.08
  lambda: 1.25
dtype: bfloat16
tokenizer_source: union