|
--- |
|
base_model: |
|
- kromeurus/L3.1-Aglow-Vulca-v0.1-8B |
|
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 |
|
- mergekit-community/L3-Boshima-a |
|
- failspy/Llama-3-8B-Instruct-MopeyMule |
|
- Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B |
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [kromeurus/L3.1-Aglow-Vulca-v0.1-8B](https://huggingface.co/kromeurus/L3.1-Aglow-Vulca-v0.1-8B) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1) |
|
* [mergekit-community/L3-Boshima-a](https://huggingface.co/mergekit-community/L3-Boshima-a) |
|
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) |
|
* [Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
dtype: float32 |
|
out_dtype: bfloat16 |
|
merge_method: model_stock |
|
base_model: kromeurus/L3.1-Aglow-Vulca-v0.1-8B |
|
models: |
|
- model: mergekit-community/L3-Boshima-a |
|
parameters: |
|
weight: 0.8 |
|
- model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 |
|
parameters: |
|
weight: 0.8 |
|
- model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B |
|
parameters: |
|
weight: 0.8 |
|
- model: kromeurus/L3.1-Aglow-Vulca-v0.1-8B |
|
parameters: |
|
weight: 0.6 |
|
- model: failspy/Llama-3-8B-Instruct-MopeyMule |
|
parameters: |
|
weight: 0.4 |
|
parameters: |
|
normalize: true |
|
|
|
``` |
|
|
