README.md

---
base_model:
- ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
- AiCloser/Qwen2.5-32B-AGI
- nbeerbower/Dumpling-Qwen2.5-32B-v2
- rinna/qwen2.5-bakeneko-32b-instruct
- Sao10K/32B-Qwen2.5-Kunou-v1
- allura-org/Qwen2.5-32b-RP-Ink
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5
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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5](https://huggingface.co/TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5) as a base.

### Models Merged

The following models were included in the merge:
* [ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3](https://huggingface.co/ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3)
* [AiCloser/Qwen2.5-32B-AGI](https://huggingface.co/AiCloser/Qwen2.5-32B-AGI)
* [nbeerbower/Dumpling-Qwen2.5-32B-v2](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2)
* [rinna/qwen2.5-bakeneko-32b-instruct](https://huggingface.co/rinna/qwen2.5-bakeneko-32b-instruct)
* [Sao10K/32B-Qwen2.5-Kunou-v1](https://huggingface.co/Sao10K/32B-Qwen2.5-Kunou-v1)
* [allura-org/Qwen2.5-32b-RP-Ink](https://huggingface.co/allura-org/Qwen2.5-32b-RP-Ink)
* [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: TheSkullery/Q2.5-Hydroblated-R1-32B-v2.5
merge_method: sce
dype: float32
out_dtype: bfloat16
tokenizer_source: Qwen/Qwen2.5-32B
Parameters:
    select_topk: 0.16
models:
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
  - model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
  - model: allura-org/Qwen2.5-32b-RP-Ink
  - model: Sao10K/32B-Qwen2.5-Kunou-v1
  - model: nbeerbower/Dumpling-Qwen2.5-32B-v2
  - model: rinna/qwen2.5-bakeneko-32b-instruct
  - model: AiCloser/Qwen2.5-32B-AGI
```