---
base_model:
- bond005/meno-tiny-0.1
- fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
- godlikehhd/alpaca_data_ifd_min_2600
- Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
- lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
- lalainy/ECE-PRYMMAL-YL-1B-SLERP-V4
- godlikehhd/alpaca_data_score_max_2500
- Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
- Sakalti/Saba1.5-1.5B
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 [bond005/meno-tiny-0.1](https://huggingface.co/bond005/meno-tiny-0.1) as a base.

### Models Merged

The following models were included in the merge:
* [fblgit/miniclaus-qw1.5B-UNAMGS-GRPO](https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS-GRPO)
* [godlikehhd/alpaca_data_ifd_min_2600](https://huggingface.co/godlikehhd/alpaca_data_ifd_min_2600)
* [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2)
* [lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3](https://huggingface.co/lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3)
* [lalainy/ECE-PRYMMAL-YL-1B-SLERP-V4](https://huggingface.co/lalainy/ECE-PRYMMAL-YL-1B-SLERP-V4)
* [godlikehhd/alpaca_data_score_max_2500](https://huggingface.co/godlikehhd/alpaca_data_score_max_2500)
* [Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1](https://huggingface.co/Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1)
* [Sakalti/Saba1.5-1.5B](https://huggingface.co/Sakalti/Saba1.5-1.5B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: bond005/meno-tiny-0.1
  - model: fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
  - model: Sakalti/Saba1.5-1.5B
  - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V1
  - model: Youlln/ECE-PRYMMAL-YL-1B-SLERP-V2
  - model: godlikehhd/alpaca_data_ifd_min_2600
  - model: godlikehhd/alpaca_data_score_max_2500
  - model: lalainy/ECE-PRYMMAL-YL-1B-SLERP-V3
  - model: lalainy/ECE-PRYMMAL-YL-1B-SLERP-V4
tokenizer:
  source: base
merge_method: sce
base_model: bond005/meno-tiny-0.1
dtype: bfloat16
parameters:
  int8_mask: true
```