|
--- |
|
base_model: |
|
- ChaoticNeutrals/RP_Vision_7B |
|
- ResplendentAI/DaturaCookie_7B |
|
- ResplendentAI/Persephone_7B |
|
- ResplendentAI/Aura_v3_7B |
|
- kainatq/Kainoverse-7b-v0.1 |
|
- ResplendentAI/Asherah_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 [kainatq/Kainoverse-7b-v0.1](https://huggingface.co/kainatq/Kainoverse-7b-v0.1) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [ChaoticNeutrals/RP_Vision_7B](https://huggingface.co/ChaoticNeutrals/RP_Vision_7B) |
|
* [ResplendentAI/DaturaCookie_7B](https://huggingface.co/ResplendentAI/DaturaCookie_7B) |
|
* [ResplendentAI/Persephone_7B](https://huggingface.co/ResplendentAI/Persephone_7B) |
|
* [ResplendentAI/Aura_v3_7B](https://huggingface.co/ResplendentAI/Aura_v3_7B) |
|
* [ResplendentAI/Asherah_7B](https://huggingface.co/ResplendentAI/Asherah_7B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: kainatq/Kainoverse-7b-v0.1 |
|
# Base model, no parameters necessary |
|
- model: ResplendentAI/Aura_v3_7B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.8 # Increased weight for potentially better general performance |
|
- model: ResplendentAI/DaturaCookie_7B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.7 # Strong, but less than Aura_v3_7B for diversity |
|
- model: ResplendentAI/Asherah_7B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.6 # Slightly lower weight for a balanced contribution |
|
- model: ResplendentAI/Persephone_7B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 # Reduced weight for minor adjustment or specific fine-tuning |
|
- model: ChaoticNeutrals/RP_Vision_7B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.6 # Balanced weight for specialized capabilities |
|
|
|
merge_method: dare_ties |
|
|
|
base_model: kainatq/Kainoverse-7b-v0.1 |
|
parameters: |
|
normalize: false |
|
int8_mask: true |
|
|
|
dtype: float16 |
|
|
|
``` |
|
|
