Hjgugugjhuhjggg/mergekit-ties-qgcitfu

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 huihui-ai/Llama-3.2-3B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• Isotonic/reasoning-llama3.2-3b
• ValiantLabs/Llama3.2-3B-ShiningValiant2
• BrainWave-ML/llama3.2-3B-codemath-orpo
• disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot
• TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient
• CK0607/llama3.2-3B-CodeP

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ValiantLabs/Llama3.2-3B-ShiningValiant2
    parameters:
      density: 0.5
      weight: 0.5
  - model: TroyDoesAI/BlackSheep-Llama3.2-3B-Context_Obedient
    parameters:
      density: 0.5
      weight: 0.5
  - model: BrainWave-ML/llama3.2-3B-codemath-orpo
    parameters:
      density: 0.5
      weight: 0.5
  - model: CK0607/llama3.2-3B-CodeP
    parameters:
      density: 0.5
      weight: 0.5
  - model: disi-unibo-nlp/llama3.2-3B-SFT-medqa-triples-cot
    parameters:
      density: 0.5
      weight: 0.5
  - model: Isotonic/reasoning-llama3.2-3b
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16