---
base_model:
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- crestf411/Q2.5-32B-Slush
- unsloth/qwen2.5-32b-instruct
- ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
- huihui-ai/Qwen2.5-32B-Instruct-abliterated
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.1
- jpacifico/Chocolatine-32B-Instruct-DPO-v1.2
- gctian/qwen2.5-32B-roleplay-zh
- nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
- JackCloudman/QwQ-32B-Preview-jackterated
library_name: transformers
tags:
- mergekit
- merge


---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/66246c2984db70bddd3f9f5f/IuVGois2JwXKn0ud3ZVpq.png)

---

# 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 [unsloth/qwen2.5-32b-instruct](https://huggingface.co/unsloth/qwen2.5-32b-instruct) as a base.

### Models Merged

The following models were included in the merge:
* [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2)
* [crestf411/Q2.5-32B-Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush)
* [ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3](https://huggingface.co/ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3)
* [huihui-ai/Qwen2.5-32B-Instruct-abliterated](https://huggingface.co/huihui-ai/Qwen2.5-32B-Instruct-abliterated)
* [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.1)
* [jpacifico/Chocolatine-32B-Instruct-DPO-v1.2](https://huggingface.co/jpacifico/Chocolatine-32B-Instruct-DPO-v1.2)
* [gctian/qwen2.5-32B-roleplay-zh](https://huggingface.co/gctian/qwen2.5-32B-roleplay-zh)
* [nbeerbower/Qwen2.5-Gutenberg-Doppel-32B](https://huggingface.co/nbeerbower/Qwen2.5-Gutenberg-Doppel-32B)
* [JackCloudman/QwQ-32B-Preview-jackterated](https://huggingface.co/JackCloudman/QwQ-32B-Preview-jackterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: crestf411/Q2.5-32B-Slush
    parameters:
      weight: 1.0
      density: 0.85
  - model: nbeerbower/Qwen2.5-Gutenberg-Doppel-32B
    parameters:
      weight: 0.30
      density: 0.77
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.1
    parameters:
      weight: 0.28
      density: 0.78
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    parameters:
      weight: 0.25
      density: 0.78
  - model: JackCloudman/QwQ-32B-Preview-jackterated
    parameters:
      weight: 0.24
      density: 0.75
  - model: jpacifico/Chocolatine-32B-Instruct-DPO-v1.2
    parameters:
      weight: 0.22
      density: 0.74
  - model: gctian/qwen2.5-32B-roleplay-zh
    parameters:
      weight: 0.20
      density: 0.75
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
    parameters:
      weight: 0.18
      density: 0.73
  - model: huihui-ai/Qwen2.5-32B-Instruct-abliterated
    parameters:
      weight: 0.15
      density: 0.70

merge_method: dare_ties
base_model: unsloth/qwen2.5-32b-instruct
parameters:
  density: 0.84
  epsilon: 0.07
  lambda: 1.25
dtype: bfloat16
tokenizer_source: union

```