---
base_model:
- Qwen/Qwen2.5-Math-1.5B-Instruct
- prithivMLmods/Bellatrix-Tiny-1.5B-R1
- Qwen/Qwen2.5-Coder-1.5B-Instruct
- Qwen/Qwen2.5-1.5B-Instruct
- justinj92/Qwen2.5-1.5B-Thinking
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the della_linear merge method using [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-Instruct)
* [prithivMLmods/Bellatrix-Tiny-1.5B-R1](https://huggingface.co/prithivMLmods/Bellatrix-Tiny-1.5B-R1)
* [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct)
* [justinj92/Qwen2.5-1.5B-Thinking](https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: della_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16
parameters:
  epsilon: 0.02
  lambda: 1.65
  normalize: true
adaptive_merge_parameters:
  task_weights:
    tinyArc: 2.2
    tinyHellaswag: 2.15
    tinyMMLU: 1.9
    tinyTruthfulQA: 2.0
    tinyTruthfulQA_mc1: 1.95
    tinyWinogrande: 1.85
    IFEval: 2.5 # Best stat, for instruction-following
    BBH: 2.2
    MATH: 2.3
    GPQA: 2.0
    MUSR: 2.0
    MMLU-PRO: 2.15
  smoothing_factor: 0.15
models:
  - model: Qwen/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: justinj92/Qwen2.5-1.5B-Thinking
    parameters:
      weight: 1
      density: 1
  - model: prithivMLmods/Bellatrix-Tiny-1.5B-R1
    parameters:
      weight: 1
      density: 1
```