base_model: | |
- MrRobotoAI/Hathor-v4.1 | |
- MrRobotoAI/Hathor-v3 | |
- MrRobotoAI/Hathor-v3.1 | |
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 linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [MrRobotoAI/Hathor-v4.1](https://huggingface.co/MrRobotoAI/Hathor-v4.1) as a base. | |
### Models Merged | |
The following models were included in the merge: | |
* [MrRobotoAI/Hathor-v3](https://huggingface.co/MrRobotoAI/Hathor-v3) | |
* [MrRobotoAI/Hathor-v3.1](https://huggingface.co/MrRobotoAI/Hathor-v3.1) | |
### Configuration | |
The following YAML configuration was used to produce this model: | |
```yaml | |
models: | |
- model: MrRobotoAI/Hathor-v3.1 | |
parameters: | |
weight: 0.55 | |
density: 0.9 | |
- model: MrRobotoAI/Hathor-v3 | |
parameters: | |
weight: 0.45 | |
density: 0.9 | |
merge_method: dare_linear | |
base_model: MrRobotoAI/Hathor-v4.1 | |
parameters: | |
normalize: true | |
dtype: float16 | |
``` | |