WesPro/MS-Instruct-ReasonableRoleplay-24B

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using mistralai/Mistral-Small-24B-Instruct-2501 as a base.

Models Merged

The following models were included in the merge:

• QuietImpostor/Mistral-R1-Preview
• cognitivecomputations/Dolphin3.0-R1-Mistral-24B
• trashpanda-org/MS-24B-Instruct-Mullein-v0
• ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
• ToastyPigeon/new-ms-rp-test-v0-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mistralai/Mistral-Small-24B-Instruct-2501
    parameters:
      density: 0.7
      weight: 0.7
  - model: ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
    parameters:
      density: 0.5
      weight: 0.5 
  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
    parameters:
      density: 0.4
      weight: 0.5
  - model: cognitivecomputations/Dolphin3.0-R1-Mistral-24B
    parameters:
      density: 0.5
      weight: 0.4
  - model: QuietImpostor/Mistral-R1-Preview
    parameters:
      density: 0.5
      weight: 0.4
  - model: ToastyPigeon/new-ms-rp-test-v0-v2
    parameters:
      density: 0.5
      weight: 0.4
merge_method: ties
base_model: mistralai/Mistral-Small-24B-Instruct-2501
parameters:
  normalize: true
  int8_mask: true
dtype: float16