|
--- |
|
base_model: |
|
- meta-llama/Meta-Llama-3-8B-Instruct |
|
- failspy/Llama-3-8B-Instruct-MopeyMule |
|
- nerdigent/L3.1-BlueSkyy-8B |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
|
|
Just an experiment using the same merge recipe as [grimjim/Llama-3-Perky-Pat-Instruct-8B](https://huggingface.co/grimjim/Llama-3-Perky-Pat-Instruct-8B) |
|
|
|
This version uses the original Llama 3 8b as a base model. I also tried this merge with 3.1 as a base, but after some quick tests I prefer this one. |
|
|
|
# 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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) |
|
* [nerdigent/L3.1-BlueSkyy-8B](https://huggingface.co/nerdigent/L3.1-BlueSkyy-8B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
base_model: meta-llama/Meta-Llama-3-8B-Instruct |
|
dtype: bfloat16 |
|
merge_method: task_arithmetic |
|
parameters: |
|
normalize: false |
|
slices: |
|
- sources: |
|
- layer_range: [0, 32] |
|
model: meta-llama/Meta-Llama-3-8B-Instruct |
|
- layer_range: [0, 32] |
|
model: nerdigent/L3.1-BlueSkyy-8B |
|
parameters: |
|
weight: 1.0 |
|
- layer_range: [0, 32] |
|
model: failspy/Llama-3-8B-Instruct-MopeyMule |
|
parameters: |
|
weight: -1.0 |
|
``` |
|
|