formulae/mita-math-v2.3-2-25-2025

merge

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

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• formulae/mita-v1.1-7b-2-24-2025
• formulae/mita-v1.2-7b-2-24-2025

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: formulae/mita-v1.1-7b-2-24-2025
    parameters:
      density: 0.6
      weight: 0.6
  - model: formulae/mita-v1.2-7b-2-24-2025
    parameters:
      density: 0.4
      weight: 0.4

merge_method: dare_linear
base_model: Qwen/Qwen2.5-Math-7B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
allow_crimes: true