70B_smrt / README.md
schonsense's picture
Add files using upload-large-folder tool
96eb260 verified
---
base_model:
- schonsense/70B_Triage
- schonsense/70B_neolithic_rabbit
- schonsense/schonsense_70B_thinkthonk
library_name: transformers
tags:
- mergekit
- merge
---
# smrt
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 D:\mergekit\yamls\IPOplectic as a base.
### Models Merged
The following models were included in the merge:
* [schonsense/70B_Triage](https://huggingface.co/schonsense/70B_Triage)
* [schonsense/70B_neolithic_rabbit](https://huggingface.co/schonsense/70B_neolithic_rabbit)
* D:\mergekit\yamls\sce_galaxy_brain
* [schonsense/schonsense_70B_thinkthonk](https://huggingface.co/schonsense/schonsense_70B_thinkthonk)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: sce
select_topk: 0.25
models:
- model: "D:\\mergekit\\yamls\\IPOplectic"
- model: "D:\\mergekit\\yamls\\sce_galaxy_brain"
- model: schonsense/70B_Triage
- model: schonsense/70B_neolithic_rabbit
- model: schonsense/schonsense_70B_thinkthonk
base_model: "D:\\mergekit\\yamls\\IPOplectic"
parameters:
normalize: false
int8_mask: true
dtype: float32
out_dtype: bfloat16
tokenizer:
source: base
pad_to_multiple_of: 8
```