---
base_model:
- chargoddard/qwamma-14b-merge-v1
- arcee-train/Qwen2.5-14B-Instruct_arcee-qwen2-14B-v0.2
- Qwen/Qwen2.5-14B
library_name: transformers
tags:
- mergekit
- merge

---
# qwamma-14b-merge-v9

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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.

### Models Merged

The following models were included in the merge:
* [chargoddard/qwamma-14b-merge-v1](https://huggingface.co/chargoddard/qwamma-14b-merge-v1)
* [arcee-train/Qwen2.5-14B-Instruct_arcee-qwen2-14B-v0.2](https://huggingface.co/arcee-train/Qwen2.5-14B-Instruct_arcee-qwen2-14B-v0.2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: ties
base_model: Qwen/Qwen2.5-14B
models:
  - model: chargoddard/qwamma-14b-merge-v1
    parameters:
      density: 1.0
      weight: 1.0
  - model: arcee-train/Qwen2.5-14B-Instruct_arcee-qwen2-14B-v0.2
    parameters:
      density: 0.66
      weight:
        - filter: mlp
          value: [0, 0.3, 0.6, 0.1]
        - filter: self_attn
          value: [0, 0, 0.2, 0.1]
        - value: 0.1
parameters:
    normalize: false
    int8_mask: true
dtype: float32
out_dtype: bfloat16


```