BioMistral-6E7B / README.md
Treza12's picture
Upload folder using huggingface_hub
e14994d verified
---
base_model:
- Treza12/Biomistral-Class2-Full
- Treza12/Biomistral-Class0-Full
- Treza12/Biomistral-Class4-Full
- Treza12/Biomistral-Class1-Full
- Treza12/Biomistral-Class5-Full
- Treza12/Biomistral-Class3-Full
- BioMistral/BioMistral-7B
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 [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) as a base.
### Models Merged
The following models were included in the merge:
* [Treza12/Biomistral-Class2-Full](https://huggingface.co/Treza12/Biomistral-Class2-Full)
* [Treza12/Biomistral-Class0-Full](https://huggingface.co/Treza12/Biomistral-Class0-Full)
* [Treza12/Biomistral-Class4-Full](https://huggingface.co/Treza12/Biomistral-Class4-Full)
* [Treza12/Biomistral-Class1-Full](https://huggingface.co/Treza12/Biomistral-Class1-Full)
* [Treza12/Biomistral-Class5-Full](https://huggingface.co/Treza12/Biomistral-Class5-Full)
* [Treza12/Biomistral-Class3-Full](https://huggingface.co/Treza12/Biomistral-Class3-Full)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Treza12/Biomistral-Class0-Full
parameters:
density: 0.5
weight: 0.5
- model: Treza12/Biomistral-Class1-Full
parameters:
density: 0.5
weight: 0.5
- model: Treza12/Biomistral-Class2-Full
parameters:
density: 0.5
weight: 0.5
- model: Treza12/Biomistral-Class3-Full
parameters:
density: 0.5
weight: 0.5
- model: Treza12/Biomistral-Class4-Full
parameters:
density: 0.5
weight: 0.5
- model: Treza12/Biomistral-Class5-Full
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: BioMistral/BioMistral-7B
parameters:
normalize: false
int8_mask: true
dtype: float16
```