Saba1-1.8B / README.md
Sakalti's picture
Upload folder using huggingface_hub
a062357 verified
|
raw
history blame
942 Bytes
---
base_model:
- micaebe/Qwen2.5-1.5B-Instruct-QwQ
- Sakalti/model-4
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Sakalti/model-4](https://huggingface.co/Sakalti/model-4) as a base.
### Models Merged
The following models were included in the merge:
* [micaebe/Qwen2.5-1.5B-Instruct-QwQ](https://huggingface.co/micaebe/Qwen2.5-1.5B-Instruct-QwQ)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: micaebe/Qwen2.5-1.5B-Instruct-QwQ
parameters:
weight: 1
density: 1
merge_method: ties
base_model: Sakalti/model-4
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: bfloat16
```