Kaoeiri/MS-Magpantheonsel-lark-v4x1.6.2RP-Cydonia-vXXX-22B-10.11

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:

• hf-100/Mistral-Small-Spellbound-StoryWriter-22B-instruct-0.2-chkpt-200-16-bit
• Gryphe/Pantheon-RP-1.6.2-22b-Small
• TroyDoesAI/BlackSheep-Mistral-22B
• TheDrummer/Cydonia-22B-v1.3
• byroneverson/Mistral-Small-Instruct-2409-abliterated + Alfitaria/mistral-small-fujin-qlora
• Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
• ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
• concedo/Beepo-22B + rAIfle/Acolyte-LORA
• TheDrummer/Cydonia-22B-v1.1
• Darkknight535/MS-Moonlight-22B-v3
• concedo/Beepo-22B + ToastyPigeon/mistral-small-springdragon-qlora
• InferenceIllusionist/SorcererLM-22B
• DigitalSouls/BlackSheep-DigitalSoul-22B
• TheDrummer/Cydonia-22B-v1.2
• crestf411/MS-sunfall-v0.7.0
• anthracite-org/magnum-v4-22b
• concedo/Beepo-22B + Kaoeiri/Moingooistrial-22B-V1-Lora

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: 0.24
      density: 0.73
  - model: TroyDoesAI/BlackSheep-Mistral-22B
    parameters:
      weight: 0.25
      density: 0.72
  - model: concedo/Beepo-22B+Kaoeiri/Moingooistrial-22B-V1-Lora
    parameters:
      weight: 0.30
      density: 0.74

  # Role-Playing Models (Low priority but important for RP)
  - model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
    parameters:
      weight: 0.13
      density: 0.64

  # Versatile, High-Performance Models
  - model: anthracite-org/magnum-v4-22b
    parameters:
      weight: 1.0
      density: 0.86
  - model: DigitalSouls/BlackSheep-DigitalSoul-22B
    parameters:
      weight: 0.19
      density: 0.68
  - model: InferenceIllusionist/SorcererLM-22B
    parameters:
      weight: 0.20
      density: 0.71
  - model: concedo/Beepo-22B+rAIfle/Acolyte-LORA
    parameters:
      weight: 0.22
      density: 0.69

  # Supporting Models (Fine-tuned for specific tasks)
  - model: TheDrummer/Cydonia-22B-v1.3
    parameters:
      weight: 0.22
      density: 0.68
  - model: TheDrummer/Cydonia-22B-v1.2
    parameters:
      weight: 0.13
      density: 0.66
  - model: TheDrummer/Cydonia-22B-v1.1
    parameters:
      weight: 0.15
      density: 0.65
  - model: crestf411/MS-sunfall-v0.7.0
    parameters:
      weight: 0.21
      density: 0.7
  - model: byroneverson/Mistral-Small-Instruct-2409-abliterated+Alfitaria/mistral-small-fujin-qlora
    parameters:
      weight: 0.16
      density: 0.68
  - model: concedo/Beepo-22B+ToastyPigeon/mistral-small-springdragon-qlora
    parameters:
      weight: 0.17
      density: 0.71
  - model: hf-100/Mistral-Small-Spellbound-StoryWriter-22B-instruct-0.2-chkpt-200-16-bit
    parameters:
      weight: 0.2
      density: 0.68

  # Additional RP-focused Models (Lower Priority)
  - model: Gryphe/Pantheon-RP-1.6.2-22b-Small
    parameters:
      weight: 0.14
      density: 0.66

  # Secondary RP-focused Models
  - model: Darkknight535/MS-Moonlight-22B-v3
    parameters:
      weight: 0.12
      density: 0.63

merge_method: dare_ties
base_model: unsloth/Mistral-Small-Instruct-2409
parameters:
  density: 0.84
  epsilon: 0.07
  lambda: 1.23
dtype: bfloat16