|
|
--- |
|
|
base_model: [] |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# top4 |
|
|
|
|
|
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using /root/top1 as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* /root/mod1 |
|
|
* /root/mod3 |
|
|
* /root/mod2 |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: /root/mod1 |
|
|
parameters: |
|
|
density: [1, 0.7, 0.1] # density gradient |
|
|
weight: 1.0 |
|
|
- model: /root/mod2 |
|
|
parameters: |
|
|
density: 0.3 |
|
|
weight: [0, 0.3, 0.7, 1] # weight gradient |
|
|
- model: /root/mod3 |
|
|
parameters: |
|
|
density: 0.1 |
|
|
weight: |
|
|
- filter: mlp |
|
|
value: 0.2 |
|
|
- value: 0 |
|
|
merge_method: ties |
|
|
base_model: /root/top1 |
|
|
parameters: |
|
|
normalize: true |
|
|
int8_mask: true |
|
|
dtype: float16 |
|
|
|
|
|
``` |
|
|
|