DareQwen-2.5-7B

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Coder-7B-Instruct
• Qwen/Qwen2.5-Math-7B-Instruct
• Qwen/Qwen2.5-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-7B
    # No parameters necessary for base model
  - model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      density: 0.6
      weight: 0.62
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
    parameters:
      density: 0.56
      weight: 0.58
  - model: Qwen/Qwen2.5-Math-7B-Instruct
    parameters:
      density: 0.6
      weight: 0.56
merge_method: dare_ties
base_model: Qwen/Qwen2.5-7B
dtype: bfloat16