---
base_model:
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2.5-Math-7B-Instruct
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
### Benchmarks

|      Tasks      |Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----------------|-------|----------------|-----:|-----------|---|-----:|---|------|
|tinyBenchmarks   |    N/A|                |      |           |   |      |   |      |
| - tinyArc       |      0|none            |    25|acc_norm   |↑  |0.2407|±  |   N/A|
| - tinyGSM8k     |      0|flexible-extract |     5|exact_match|↑  |0.0055|±  |   N/A|
|                 |       |strict-match    |     5|exact_match|↑  |0.0055|±  |   N/A|
| - tinyHellaswag |      0|none            |    10|acc_norm   |↑  |0.3322|±  |   N/A|
| - tinyMMLU      |      0|none            |     0|acc_norm   |↑  |0.2839|±  |   N/A|
| - tinyTruthfulQA|      0|none            |     0|acc        |↑  |   NaN|±  |   N/A|
| - tinyWinogrande|      0|none            |     5|acc_norm   |↑  |0.4491|±  |   N/A|

### Merge Method

This model was merged using the NuSLERP merge method.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
* [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: Qwen/Qwen2.5-7B-Instruct
        layer_range: [0, 7]
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [0, 7]
    parameters:
      weight: [0.85, 0.15]
      nuslerp_flatten: false

  - sources:
      - model: Qwen/Qwen2.5-7B-Instruct
        layer_range: [7, 14]
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [7, 14]
    parameters:
      weight: [0.6, 0.4]
      nuslerp_flatten: false

  - sources:
      - model: Qwen/Qwen2.5-7B-Instruct
        layer_range: [14, 21]
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [14, 21]
    parameters:
      weight: [0.4, 0.6]
      nuslerp_flatten: false

  - sources:
      - model: Qwen/Qwen2.5-7B-Instruct
        layer_range: [21, 28]
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [21, 28]
    parameters:
      weight: [0.3, 0.7]
      nuslerp_flatten: false

merge_method: nuslerp
dtype: float16

```