|
---
|
|
base_model: []
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Ninja-v1-RP-expressive-v2
|
|
|
|
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 breadcrumbs_ties merge method using ./Ninja-v1-RP-v2 as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* ./Antler-7B-MS
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: ./Ninja-v1-RP-v2
|
|
# no parameters necessary for base model
|
|
- model: ./Antler-7B-MS
|
|
parameters:
|
|
weight: 0.5
|
|
merge_method: breadcrumbs_ties
|
|
base_model: ./Ninja-v1-RP-v2
|
|
dtype: bfloat16
|
|
tokenizer_source: union
|
|
parameters:
|
|
density: 0.9
|
|
gamma: 0.01
|
|
|
|
```
|
|
|
