|
|
--- |
|
|
base_model: |
|
|
- tinycompany/Tamed-Sigma |
|
|
- tinycompany/Tamed-Sigma-hi |
|
|
- tinycompany/SigmaBoi-Instruct-nomic |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# model3 |
|
|
|
|
|
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 TIES](https://arxiv.org/abs/2311.03099) merge method using [tinycompany/Tamed-Sigma-hi](https://huggingface.co/tinycompany/Tamed-Sigma-hi) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [tinycompany/Tamed-Sigma](https://huggingface.co/tinycompany/Tamed-Sigma) |
|
|
* [tinycompany/SigmaBoi-Instruct-nomic](https://huggingface.co/tinycompany/SigmaBoi-Instruct-nomic) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
base_model: tinycompany/Tamed-Sigma-hi |
|
|
dtype: bfloat16 |
|
|
merge_method: dare_ties |
|
|
parameters: |
|
|
int8_mask: 1.0 |
|
|
normalize: 0.0 |
|
|
slices: |
|
|
- sources: |
|
|
- layer_range: [0, 6] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.6 |
|
|
- layer_range: [0, 6] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 0.6 |
|
|
weight: 0.5 |
|
|
- layer_range: [0, 6] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.5 |
|
|
- sources: |
|
|
- layer_range: [6, 12] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 0.8 |
|
|
weight: 0.1 |
|
|
- layer_range: [6, 12] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.2 |
|
|
- layer_range: [6, 12] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.7 |
|
|
- sources: |
|
|
- layer_range: [12, 18] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 0.7 |
|
|
weight: 0.1 |
|
|
- layer_range: [12, 18] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 0.7 |
|
|
weight: 0.2 |
|
|
- layer_range: [12, 18] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 0.7 |
|
|
weight: 0.6 |
|
|
- sources: |
|
|
- layer_range: [18, 24] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 0.9 |
|
|
weight: 0.2 |
|
|
- layer_range: [18, 24] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 0.6 |
|
|
weight: 0.6 |
|
|
- layer_range: [18, 24] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 0.7 |
|
|
weight: 0.3 |
|
|
- sources: |
|
|
- layer_range: [24, 30] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.2 |
|
|
- layer_range: [24, 30] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.2 |
|
|
- layer_range: [24, 30] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 0.9 |
|
|
weight: 0.4 |
|
|
- sources: |
|
|
- layer_range: [30, 36] |
|
|
model: tinycompany/Tamed-Sigma |
|
|
parameters: |
|
|
density: 0.7 |
|
|
weight: 0.2 |
|
|
- layer_range: [30, 36] |
|
|
model: tinycompany/SigmaBoi-Instruct-nomic |
|
|
parameters: |
|
|
density: 0.9 |
|
|
weight: 0.3 |
|
|
- layer_range: [30, 36] |
|
|
model: tinycompany/Tamed-Sigma-hi |
|
|
parameters: |
|
|
density: 1.0 |
|
|
weight: 0.4 |
|
|
|
|
|
``` |
|
|
|
