|
Basically, I took an excellent chat llm that has some weird hangups in RP, and merged it with a bunch of ERP models |
|
GGUF - [nocudaexe/Infinite-Waifu-7b-GGUF](https://huggingface.co/nocudaexe/Infinite-Waifu-7b-GGUF) |
|
|
|
--- |
|
base_model: |
|
[Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B) |
|
|
|
[Test157t/Kunocchini-7b-128k-test](https://huggingface.co/Test157t/Kunocchini-7b-128k-test) |
|
|
|
[mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) |
|
|
|
[KatyTheCutie/SlushySlerp-7B](KatyTheCutie/SlushySlerp-7B) |
|
|
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# 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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B) |
|
* [Test157t/Kunocchini-7b-128k-test](https://huggingface.co/Test157t/Kunocchini-7b-128k-test) |
|
* [KatyTheCutie/SlushySlerp-7B](https://huggingface.co/KatyTheCutie/SlushySlerp-7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: mlabonne/AlphaMonarch-7B |
|
# No parameters necessary for base model |
|
- model: Test157t/Kunocchini-7b-128k-test |
|
parameters: |
|
density: 0.43 |
|
weight: 0.4 |
|
- model: KatyTheCutie/SlushySlerp-7B |
|
parameters: |
|
density: 0.33 |
|
weight: 0.3 |
|
- model: Endevor/InfinityRP-v1-7B |
|
parameters: |
|
density: 0.3 |
|
weight: 0.3 |
|
merge_method: dare_ties |
|
base_model: mlabonne/AlphaMonarch-7B |
|
parameters: |
|
int8_mask: true |
|
dtype: bfloat16 |
|
|
|
``` |
|
|