nilq's picture
Update README.md
a0b1aea verified
---
base_model:
- nilq/baby-python-mistral-1L-tiny-lua-ft
- nilq/baby-python-mistral-1L-tiny-TinyStories-ft
library_name: transformers
tags:
- mergekit
- merge
---
# baby-python-1L-mistral-lua-stories-slerp
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). This is the LuaStories model in the paper [Tracking Universal Features Through Fine-Tuning and Model Merging](https://arxiv.org/abs/2410.12391).
## Merge Details
### Merge Method
This model was merged using the SLERP merge method.
### Models Merged
The following models were included in the merge:
* [nilq/baby-python-mistral-1L-tiny-lua-ft](https://huggingface.co/nilq/baby-python-mistral-1L-tiny-lua-ft)
* [nilq/baby-python-mistral-1L-tiny-TinyStories-ft](https://huggingface.co/nilq/baby-python-mistral-1L-tiny-TinyStories-ft)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nilq/baby-python-mistral-1L-tiny-lua-ft
- model: nilq/baby-python-mistral-1L-tiny-TinyStories-ft
merge_method: slerp
base_model: nilq/baby-python-mistral-1L-tiny-lua-ft
parameters:
t:
- value: 0.58
dtype: float16
```