Derrick30 / README.md
Sumail's picture
Upload folder using huggingface_hub
8f1e32a verified
---
base_model:
- deepnetguy/gemma-127
- deepnetguy/gemma-126
- tomaszki/gemma-44
- rwh/gemma2
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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [deepnetguy/gemma-126](https://huggingface.co/deepnetguy/gemma-126) as a base.
### Models Merged
The following models were included in the merge:
* [deepnetguy/gemma-127](https://huggingface.co/deepnetguy/gemma-127)
* [tomaszki/gemma-44](https://huggingface.co/tomaszki/gemma-44)
* [rwh/gemma2](https://huggingface.co/rwh/gemma2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: deepnetguy/gemma-126
# No parameters necessary for base model
- model: deepnetguy/gemma-127
parameters:
density: 0.53
weight: 0.3
- model: rwh/gemma2
parameters:
density: 0.53
weight: 0.4
- model: tomaszki/gemma-44
parameters:
density: 0.53
weight: 0.25
merge_method: dare_ties
base_model: deepnetguy/gemma-126
parameters:
int8_mask: true
dtype: bfloat16
```