|
--- |
|
base_model: [] |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# ninja |
|
|
|
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 Kunoichi-7B as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* notus-7b-v1 |
|
* openchat_3.5 |
|
* Loyal-Macaroni-Maid-7B |
|
|
|
+ some ERP LoRA I made |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Kunoichi-7B |
|
- model: Loyal-Macaroni-Maid-7B |
|
parameters: |
|
density: 0.53 |
|
weight: 0.7 |
|
- model: notus-7b-v1 |
|
parameters: |
|
density: 0.53 |
|
weight: 0.2 |
|
- model: openchat_3.5 |
|
parameters: |
|
density: 0.53 |
|
weight: 0.1 |
|
merge_method: dare_ties |
|
base_model: Kunoichi-7B |
|
parameters: |
|
int8_mask: true |
|
tokenizer_source: union |
|
dtype: bfloat16 |
|
``` |
|
|
