MegaMix_4B / README.md
jeiku's picture
Upload folder using huggingface_hub
11b36f2 verified
---
base_model:
- FourOhFour/NeuroCom_4B
- FourOhFour/NeuroCom_v2_4B
- FourOhFour/Luxe_4B
- FourOhFour/QuantuMinx_4B
- FourOhFour/Maelstrom_4B
- FourOhFour/Poe_4B
- FourOhFour/Deedlit_4B
- FourOhFour/Zenith_4B
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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [FourOhFour/Zenith_4B](https://huggingface.co./FourOhFour/Zenith_4B) as a base.
### Models Merged
The following models were included in the merge:
* [FourOhFour/NeuroCom_4B](https://huggingface.co./FourOhFour/NeuroCom_4B)
* [FourOhFour/NeuroCom_v2_4B](https://huggingface.co./FourOhFour/NeuroCom_v2_4B)
* [FourOhFour/Luxe_4B](https://huggingface.co./FourOhFour/Luxe_4B)
* [FourOhFour/QuantuMinx_4B](https://huggingface.co./FourOhFour/QuantuMinx_4B)
* [FourOhFour/Maelstrom_4B](https://huggingface.co./FourOhFour/Maelstrom_4B)
* [FourOhFour/Poe_4B](https://huggingface.co./FourOhFour/Poe_4B)
* [FourOhFour/Deedlit_4B](https://huggingface.co./FourOhFour/Deedlit_4B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: task_arithmetic
base_model: FourOhFour/Zenith_4B
parameters:
normalize: true
models:
- model: FourOhFour/Deedlit_4B
parameters:
weight: 0.3
- model: FourOhFour/NeuroCom_4B
parameters:
weight: 0.1
- model: FourOhFour/NeuroCom_v2_4B
parameters:
weight: 0.1
- model: FourOhFour/Zenith_4B
parameters:
weight: 0.3
- model: FourOhFour/QuantuMinx_4B
parameters:
weight: 0.1
- model: FourOhFour/Luxe_4B
parameters:
weight: 0.2
- model: FourOhFour/Maelstrom_4B
parameters:
weight: 0.1
- model: FourOhFour/Poe_4B
parameters:
weight: 0.1
dtype: bfloat16
```