|
---
|
|
base_model: []
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Oumuamua-7b-RP
|
|
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using Oumuamua-7b-RP\Oumuamua-RP-breadcrumbs as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-Kunoichi
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-LemonadeRP
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-LoyalMacaroniMaid
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-Berghof
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-WestLake
|
|
* Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-InfinityRP
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
base_model: Oumuamua-7b-RP\Oumuamua-RP-breadcrumbs
|
|
dtype: bfloat16
|
|
merge_method: model_stock
|
|
slices:
|
|
- sources:
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-Kunoichi
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-WestLake
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-LemonadeRP
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-InfinityRP
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-LoyalMacaroniMaid
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-7b-instruct-v2-RP-preset-Berghof
|
|
- layer_range: [0, 32]
|
|
model: Oumuamua-7b-RP\Oumuamua-RP-breadcrumbs
|
|
tokenizer_source: base
|
|
```
|
|
|
