---
base_model:
- Qwen/Qwen2.5-14B
- allknowingroger/QwenSlerp6-14B
- allknowingroger/QwenStock3-14B
- CultriX/SeQwence-14B-EvolMerge
- CultriX/Qwen2.5-14B-Wernicke
- VAGOsolutions/SauerkrautLM-v2-14b-DPO
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 [DARE](https://arxiv.org/abs/2311.03099) [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:
* [allknowingroger/QwenSlerp6-14B](https://huggingface.co/allknowingroger/QwenSlerp6-14B)
* [allknowingroger/QwenStock3-14B](https://huggingface.co/allknowingroger/QwenStock3-14B)
* [CultriX/SeQwence-14B-EvolMerge](https://huggingface.co/CultriX/SeQwence-14B-EvolMerge)
* [CultriX/Qwen2.5-14B-Wernicke](https://huggingface.co/CultriX/Qwen2.5-14B-Wernicke)
* [VAGOsolutions/SauerkrautLM-v2-14b-DPO](https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-DPO)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
### CONFIG SuperiorMerge-14B-From-2-to-10 ###

models:
  - model: VAGOsolutions/SauerkrautLM-v2-14b-DPO
    parameters:
      weight: 0.25    # Prioritize top IFEval
      density: 0.6     # Keep a large portion for strong factual baseline

  - model: allknowingroger/QwenSlerp6-14B
    parameters:
      weight: 0.25    # High weight for MATH and balanced reasoning
      density: 0.6     # Retain robust reasoning capabilities

  - model: CultriX/SeQwence-14B-EvolMerge
    parameters:
      weight: 0.20    # Important for best BBH and near-top MUSR
      density: 0.5     # Moderate density to ensure these strengths blend well

  - model: CultriX/Qwen2.5-14B-Wernicke
    parameters:
      weight: 0.15    # Adds top GPQA performance
      density: 0.5     # Sufficient to preserve QA strengths

  - model: allknowingroger/QwenStock3-14B
    parameters:
      weight: 0.15    # For top MMLU-PRO, enhancing domain knowledge
      density: 0.5     # Balanced integration of diverse subject expertise

base_model: Qwen/Qwen2.5-14B
merge_method: dare_ties
parameters:
  normalize: true      # Ensures parameter scaling compatibility
  int8_mask: true      # Memory and computational efficiency
dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-14B-Instruct

### END OF CONFIG SuperiorMerge-14B-From-2-to-10 ###

```