Mixtral_Instruct_7b / README.md
LeroyDyer's picture
Update README.md
0e658a9 verified
|
raw
history blame
988 Bytes
---
base_model:
- Locutusque/Hercules-3.1-Mistral-7B
- LeroyDyer/Mixtral_BaseModel
library_name: transformers
tags:
- mergekit
- merge
license: mit
language:
- en
metrics:
- bleu
- accuracy
---
# MODEL_NAME
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](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* [Locutusque/Hercules-3.1-Mistral-7B](https://huggingface.co/Locutusque/Hercules-3.1-Mistral-7B)
* [LeroyDyer/Mixtral_BaseModel](https://huggingface.co/LeroyDyer/Mixtral_BaseModel)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: LeroyDyer/Mixtral_BaseModel
parameters:
weight: 1.0
- model: Locutusque/Hercules-3.1-Mistral-7B
parameters:
weight: 0.6
merge_method: linear
dtype: float16
```