bunnycore/Qwen2-7b-Max-dare

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 Qwen/Qwen2-7B as a base.

Models Merged

The following models were included in the merge:

• augmxnt/Qwen2-7B-Instruct-deccp
• arcee-ai/Arcee-Spark
• macadeliccc/Samantha-Qwen-2-7B
• natong19/Qwen2-7B-Instruct-abliterated
• cognitivecomputations/dolphin-2.9.2-qwen2-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: arcee-ai/Arcee-Spark
    parameters:
      density: 0.5
      weight: 0.5
  - model: natong19/Qwen2-7B-Instruct-abliterated
    parameters:
      density: 0.5
      weight: 0.5
  - model: cognitivecomputations/dolphin-2.9.2-qwen2-7b
    parameters:
      density: 0.5
      weight: 0.5
  - model: macadeliccc/Samantha-Qwen-2-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: augmxnt/Qwen2-7B-Instruct-deccp
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: Qwen/Qwen2-7B
parameters:
  normalize: false
  int8_mask: true
dtype: float16