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/Qwen2.5-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
dtype: bfloat16
normalize: true
base_model: Qwen/Qwen2.5-3B-Instruct
models:
  - model: PowerInfer/SmallThinker-3B-Preview  # CoT 2 - Detailed & Nuanced
    parameters:
      weight: 0.4
      density: 0.7
  - model: prithivMLmods/QwQ-LCoT-3B-Instruct  # CoT 3 - Structured & Focused
    parameters:
      weight: 0.6
      density: 0.8