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:
  # Obedience and Strong Replies
  - model: qingy2024/MwM-22B-Instruct
    parameters:
      weight: 1.2
      density: 0.8
  - model: DigitalSouls/BlackSheep-DigitalSoul-22B
    parameters:
      weight: 0.8
      density: 0.85
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.7
      density: 0.85

  # RP and Storytelling
  - model: Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-8
    parameters:
      weight: 0.68
      density: 0.75
  - model: TheDrummer/Cydonia-22B-v1.3
    parameters:
      weight: 0.33
      density: 0.7
  - model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
    parameters:
      weight: 0.5
      density: 0.7

  # Background and Additional Features
  - model: Darkknight535/MS-Moonlight-22B-v3
    parameters:
      weight: 0.3
      density: 0.7
  - model: InferenceIllusionist/SorcererLM-22B
    parameters:
      weight: 0.34
      density: 0.7
  - model: Envoid/Mistral-Small-NovusKyver
    parameters:
      weight: 0.3
      density: 0.7
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.4
      density: 0.75
  - model: Kaoeiri/MS_a-coolyte-2409-22B
    parameters:
      weight: 0.32
      density: 0.7
  - model: invisietch/MiS-Firefly-v0.2-22B
    parameters:
      weight: 0.34
      density: 0.7
  - model: Kaoeiri/MS_fujin-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 0.56
      density: 0.7
  - model: allura-org/MS-Meadowlark-22B
    parameters:
      weight: 0.35
      density: 0.7
  - model: Saxo/Linkbricks-Horizon-AI-Korean-Superb-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS_Moingooistral-2409-22B
    parameters:
      weight: 0.3
      density: 0.7
  - model: Kaoeiri/MS-Inky-2409-22B
    parameters:
      weight: 0.3
      density: 0.7

merge_method: dare_ties
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.90
  epsilon: 0.08
  lambda: 1.18
  normalize: true
dtype: bfloat16
Downloads last month
2
Safetensors
Model size
22.2B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Kaoeiri/MS-MagpantheonselRP-22B-14.95-Omen