|
--- |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- mistral |
|
- roleplay |
|
--- |
|
|
|
## Info |
|
|
|
This one is unhinged. Same idea as previous version, but added [ResplendentAI/Pandora_7B](https://huggingface.co/ResplendentAI/Pandora_7B). |
|
|
|
SillyTavern [presets included](https://huggingface.co/Virt-io/Irene-RP-v2-7B/tree/main/presets). |
|
|
|
When using the presets you will need to set example massages to never send. Or they will be sent twice. |
|
|
|
<img src="https://huggingface.co/Virt-io/Irene-RP-v2-7B/resolve/main/presets/ExampleMessages.png"> |
|
|
|
___ |
|
# Irene-RP-v2-7B |
|
|
|
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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* Mergekit/Eros-Erebus-Holodeck-7B |
|
* [ResplendentAI/Pandora_7B](https://huggingface.co/ResplendentAI/Pandora_7B) |
|
* [Virt-io/Nina-v2-7B](https://huggingface.co/Virt-io/Nina-v2-7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: Endevor/InfinityRP-v1-7B |
|
parameters: |
|
weight: 1.0 |
|
- model: Virt-io/Nina-v2-7B |
|
parameters: |
|
weight: 0.55 |
|
- model: Mergekit/Eros-Erebus-Holodeck-7B |
|
parameters: |
|
weight: 0.65 |
|
- model: ResplendentAI/Pandora_7B |
|
parameters: |
|
weight: 0.55 |
|
merge_method: task_arithmetic |
|
base_model: Endevor/InfinityRP-v1-7B |
|
parameters: |
|
normalize: true |
|
int8_mask: true |
|
dtype: float16 |
|
|
|
``` |
|
|
