|
|
---
|
|
|
base_model:
|
|
|
- TareksLab/Erudite-V1-Unleashed-LLaMA-70B
|
|
|
- TareksLab/RolePlayer-V4-LLaMa-70B
|
|
|
- TareksLab/Anathema-V2-LLaMA-70B
|
|
|
- TareksLab/Wordsmith-V2.0-LLaMa-70B
|
|
|
- TareksLab/Scrivener-Base-V4-LLaMA-70B
|
|
|
library_name: transformers
|
|
|
tags:
|
|
|
- mergekit
|
|
|
- merge
|
|
|
|
|
|
---
|
|
|
# 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 [TareksLab/Erudite-V1-Unleashed-LLaMA-70B](https://huggingface.co/TareksLab/Erudite-V1-Unleashed-LLaMA-70B) as a base.
|
|
|
|
|
|
### Models Merged
|
|
|
|
|
|
The following models were included in the merge:
|
|
|
* [TareksLab/RolePlayer-V4-LLaMa-70B](https://huggingface.co/TareksLab/RolePlayer-V4-LLaMa-70B)
|
|
|
* [TareksLab/Anathema-V2-LLaMA-70B](https://huggingface.co/TareksLab/Anathema-V2-LLaMA-70B)
|
|
|
* [TareksLab/Wordsmith-V2.0-LLaMa-70B](https://huggingface.co/TareksLab/Wordsmith-V2.0-LLaMa-70B)
|
|
|
* [TareksLab/Scrivener-Base-V4-LLaMA-70B](https://huggingface.co/TareksLab/Scrivener-Base-V4-LLaMA-70B)
|
|
|
|
|
|
### Configuration
|
|
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
|
|
```yaml
|
|
|
models:
|
|
|
- model: TareksLab/Wordsmith-V2.0-LLaMa-70B
|
|
|
- model: TareksLab/Anathema-V2-LLaMA-70B
|
|
|
- model: TareksLab/Scrivener-Base-V4-LLaMA-70B
|
|
|
- model: TareksLab/RolePlayer-V4-LLaMa-70B
|
|
|
merge_method: sce
|
|
|
base_model: TareksLab/Erudite-V1-Unleashed-LLaMA-70B
|
|
|
parameters:
|
|
|
select_topk: 0.16
|
|
|
dtype: bfloat16
|
|
|
tokenizer:
|
|
|
source: TareksLab/Scrivener-Base-V4-LLaMA-70B
|
|
|
```
|
|
|
|
