---
base_model:
- rombodawg/Rombos-LLM-V2.5-Qwen-7b
- fblgit/cybertron-v4-qw7B-MGS
- Qwen/Qwen2.5-7B
library_name: transformers
tags:
- wizard
- merge
- qwen2
- ties
---

# Qwen2.5-7B-CyberRombos-Wizard

This is a merge of pre-trained language models created using [Wizard](https://github.com/mindspore-lab/mindnlp), reproducing the [TIES](https://arxiv.org/abs/2306.01708) configuration of [bunnycore/Qwen2.5-7B-CyberRombos](https://huggingface.co/bunnycore/Qwen2.5-7B-CyberRombos).

## Merge Details

### Merge Method

This model was merged using the **TIES** merge method with [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as the base.

### Models Merged

The following models were included in the merge:

- [rombodawg/Rombos-LLM-V2.5-Qwen-7b](https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-7b)
- [fblgit/cybertron-v4-qw7B-MGS](https://huggingface.co/fblgit/cybertron-v4-qw7B-MGS)

### Configuration

```yaml
models:
  - model: rombodawg/Rombos-LLM-V2.5-Qwen-7b
    parameters:
      density: 0.5
      weight: 0.5
  - model: fblgit/cybertron-v4-qw7B-MGS
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: Qwen/Qwen2.5-7B
parameters:
  normalize: false
  int8_mask: true
dtype: float16
```

## Citation

TIES: [Resolving Interference When Merging Models](https://arxiv.org/abs/2306.01708) (Yadav et al., 2023).