Smort_3B / README.md
jeiku's picture
Upload 10 files
462a419 verified
|
raw
history blame
2.03 kB
---
base_model:
- jeiku/Linear_Base_3B
- jeiku/Theory_of_Mind_128_StableLM
- jeiku/Linear_Base_3B
- jeiku/Gnosis_StableLM
- jeiku/Linear_Base_3B
- jeiku/No_Robots_Alpaca_StableLM
- jeiku/Linear_Base_3B
- jeiku/Toxic_DPO_StableLM
- jeiku/Linear_Base_3B
- jeiku/Everything_v3_128_StableLM
tags:
- mergekit
- merge
---
# Mixed
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 [linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* [jeiku/Linear_Base_3B](https://huggingface.co/jeiku/Linear_Base_3B) + [jeiku/Theory_of_Mind_128_StableLM](https://huggingface.co/jeiku/Theory_of_Mind_128_StableLM)
* [jeiku/Linear_Base_3B](https://huggingface.co/jeiku/Linear_Base_3B) + [jeiku/Gnosis_StableLM](https://huggingface.co/jeiku/Gnosis_StableLM)
* [jeiku/Linear_Base_3B](https://huggingface.co/jeiku/Linear_Base_3B) + [jeiku/No_Robots_Alpaca_StableLM](https://huggingface.co/jeiku/No_Robots_Alpaca_StableLM)
* [jeiku/Linear_Base_3B](https://huggingface.co/jeiku/Linear_Base_3B) + [jeiku/Toxic_DPO_StableLM](https://huggingface.co/jeiku/Toxic_DPO_StableLM)
* [jeiku/Linear_Base_3B](https://huggingface.co/jeiku/Linear_Base_3B) + [jeiku/Everything_v3_128_StableLM](https://huggingface.co/jeiku/Everything_v3_128_StableLM)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: jeiku/Linear_Base_3B+jeiku/Everything_v3_128_StableLM
parameters:
weight: 1.0
- model: jeiku/Linear_Base_3B+jeiku/Theory_of_Mind_128_StableLM
parameters:
weight: 1.0
- model: jeiku/Linear_Base_3B+jeiku/Toxic_DPO_StableLM
parameters:
weight: 1.0
- model: jeiku/Linear_Base_3B+jeiku/No_Robots_Alpaca_StableLM
parameters:
weight: 1.0
- model: jeiku/Linear_Base_3B+jeiku/Gnosis_StableLM
parameters:
weight: 1.0
merge_method: linear
dtype: float16
```