Winter-8B-SCE / README.md
DreadPoor's picture
Update README.md
f4b7905 verified
---
base_model:
- DreadPoor/BaeZel-8B-LINEAR
- FuseAI/FuseChat-Llama-3.1-8B-SFT
- DreadPoor/OrangeJ-8B-Model_Stock
- DreadPoor/Aspire-8B-model_stock
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
---
# 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 [SCE](https://arxiv.org/abs/2408.07990) merge method using [FuseAI/FuseChat-Llama-3.1-8B-SFT](https://huggingface.co./FuseAI/FuseChat-Llama-3.1-8B-SFT) as a base.
### Models Merged
The following models were included in the merge:
* [DreadPoor/BaeZel-8B-LINEAR](https://huggingface.co./DreadPoor/BaeZel-8B-LINEAR)
* [DreadPoor/OrangeJ-8B-Model_Stock](https://huggingface.co./DreadPoor/OrangeJ-8B-Model_Stock)
* [DreadPoor/Aspire-8B-model_stock](https://huggingface.co./DreadPoor/Aspire-8B-model_stock)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: DreadPoor/BaeZel-8B-LINEAR
- model: DreadPoor/Aspire-8B-model_stock
- model: DreadPoor/OrangeJ-8B-Model_Stock
merge_method: sce
base_model: FuseAI/FuseChat-Llama-3.1-8B-SFT
parameters:
select_topk: 0.4
dtype: bfloat16
```