bunnycore/Qwen2.5-7B-HyperMix

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 Orion-zhen/Qwen2.5-7B-Instruct-Uncensored as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
• Replete-AI/Replete-LLM-V2.5-Qwen-7b
• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.0

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
    parameters:
      density: 0.5
      weight: 0.5
  - model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2
    parameters:
      density: 0.5
      weight: 0.4
  - model: Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
    parameters:
      density: 0.5
      weight: 0.5
  - model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.0
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
parameters:
  normalize: false
  int8_mask: true
dtype: float16