Lunzima's picture
Upload folder using huggingface_hub
d50815b verified
---
base_model:
- hotmailuser/QwenSlerp2-14B
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2
- sometimesanotion/Qwenvergence-14B-v12-Prose-DS
- Sakalti/Saka-14B
- jpacifico/Chocolatine-2-14B-Instruct-v2.0.3
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-1
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Sakalti/Saka-14B](https://huggingface.co/Sakalti/Saka-14B) as a base.
### Models Merged
The following models were included in the merge:
* [hotmailuser/QwenSlerp2-14B](https://huggingface.co/hotmailuser/QwenSlerp2-14B)
* [Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2](https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2)
* [sometimesanotion/Qwenvergence-14B-v12-Prose-DS](https://huggingface.co/sometimesanotion/Qwenvergence-14B-v12-Prose-DS)
* [jpacifico/Chocolatine-2-14B-Instruct-v2.0.3](https://huggingface.co/jpacifico/Chocolatine-2-14B-Instruct-v2.0.3)
* [Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-1](https://huggingface.co/Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
name: NQLSG-Qwen2.5-14B-MegaFusion-TIES-3
models:
- model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-1
- model: Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-2
- model: hotmailuser/QwenSlerp2-14B
- model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS
- model: jpacifico/Chocolatine-2-14B-Instruct-v2.0.3
- model: Sakalti/Saka-14B
base_model: Sakalti/Saka-14B
chat_template: auto
dtype: bfloat16
merge_method: ties
parameters:
weight: 1.0
density: 1.0
normalize: true
int8_mask: true
tokenizer:
source: union
```