40 lines
907 B
Markdown
40 lines
907 B
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- vicgalle/Configurable-Mistral-7B
|
||
|
|
- kaist-ai/janus-dpo-7b
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
license: mit
|
||
|
|
---
|
||
|
|
# 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](https://arxiv.org/abs/2203.05482) merge method.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [vicgalle/Configurable-Mistral-7B](https://huggingface.co/vicgalle/Configurable-Mistral-7B)
|
||
|
|
* [kaist-ai/janus-dpo-7b](https://huggingface.co/kaist-ai/janus-dpo-7b)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
models:
|
||
|
|
- model: vicgalle/Configurable-Mistral-7B
|
||
|
|
parameters:
|
||
|
|
weight: 1.0
|
||
|
|
- model: kaist-ai/janus-dpo-7b
|
||
|
|
parameters:
|
||
|
|
weight: 1.0
|
||
|
|
merge_method: linear
|
||
|
|
dtype: float16
|
||
|
|
```
|