README.md

---
base_model:
- nbeerbower/Dumpling-Qwen2.5-32B
- rinna/qwen2.5-bakeneko-32b-instruct
- EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
- zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
- nbeerbower/Dumpling-Qwen2.5-32B-v2
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---

![image/png](https://huggingface.co/nbeerbower/Azura-Qwen2.5-32B/resolve/main/cover.png?download=true)
# Azura-Qwen2.5-32B

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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [nbeerbower/Dumpling-Qwen2.5-32B](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B) as a base.

### Models Merged

The following models were included in the merge:
* [rinna/qwen2.5-bakeneko-32b-instruct](https://huggingface.co/rinna/qwen2.5-bakeneko-32b-instruct)
* [EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2)
* [zetasepic/Qwen2.5-32B-Instruct-abliterated-v2](https://huggingface.co/zetasepic/Qwen2.5-32B-Instruct-abliterated-v2)
* [nbeerbower/Dumpling-Qwen2.5-32B-v2](https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-32B-v2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: zetasepic/Qwen2.5-32B-Instruct-abliterated-v2
  - model: nbeerbower/Dumpling-Qwen2.5-32B-v2
  - model: EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
  - model: rinna/qwen2.5-bakeneko-32b-instruct
merge_method: model_stock
base_model: nbeerbower/Dumpling-Qwen2.5-32B
dtype: bfloat16


```