README.md

---
base_model:
- prithivMLmods/Phi-4-Math-IO
- prithivMLmods/Phi-4-QwQ
- prithivMLmods/Phi-4-o1
- prithivMLmods/Phi-4-Empathetic
library_name: transformers
tags:
- mergekit
- merge
---
![omni.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/JTKBiJLxpEZJJc6Uiv47m.png)

# **Merge Phi4 Based**

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 [prithivMLmods/Phi-4-o1](https://huggingface.co/prithivMLmods/Phi-4-o1) as a base.

### Models Merged

The following models were included in the merge:
* [prithivMLmods/Phi-4-Math-IO](https://huggingface.co/prithivMLmods/Phi-4-Math-IO)
* [prithivMLmods/Phi-4-QwQ](https://huggingface.co/prithivMLmods/Phi-4-QwQ)
* [prithivMLmods/Phi-4-Empathetic](https://huggingface.co/prithivMLmods/Phi-4-Empathetic)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: prithivMLmods/Phi-4-o1
  - model: prithivMLmods/Phi-4-Math-IO
  - model: prithivMLmods/Phi-4-QwQ
  - model: prithivMLmods/Phi-4-Empathetic
merge_method: model_stock
base_model: prithivMLmods/Phi-4-o1
normalize: true
int8_mask: true
dtype: bfloat16
```