Qwen-3B-Instruct-Breadcrumbs-Ties-v1

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

Merge Details

Merge Method

This model was merged using the Model Breadcrumbs with TIES merge method using Qwen/Qwen2.5-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

• Alelcv27/Qwen2.5-3B-Instruct-Math-CoT
• Alelcv27/Qwen2.5-3B-Instruct-Code

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-3B-Instruct
dtype: float16
merge_method: breadcrumbs_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 36]
        model: Alelcv27/Qwen2.5-3B-Instruct-Code
        parameters:
          density: 0.5
          weight: 0.8
      - layer_range: [0, 36]
        model: Alelcv27/Qwen2.5-3B-Instruct-Math-CoT
        parameters:
          density: 0.6
          weight: 0.9
      - layer_range: [0, 36]
        model: Qwen/Qwen2.5-3B-Instruct
parameters:
  normalize: 1.0