base_model: | |
- HuggingFaceH4/zephyr-7b-beta | |
library_name: transformers | |
tags: | |
- mergekit | |
- merge | |
# zephyr-dpo-v7-beta-slerp | |
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 mergekit/zephyr-merged-dpo-v7-multi as a base. | |
### Models Merged | |
The following models were included in the merge: | |
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | |
### Configuration | |
The following YAML configuration was used to produce this model: | |
```yaml | |
models: | |
- model: mergekit/zephyr-merged-dpo-v7-multi | |
- model: HuggingFaceH4/zephyr-7b-beta | |
parameters: | |
density: 0.2 | |
weight: # weight gradient | |
- filter: mlp | |
value: 0.2 | |
- value: 0.1 | |
merge_method: ties | |
base_model: mergekit/zephyr-merged-dpo-v7-multi | |
parameters: | |
normalize: true | |
int8_mask: true | |
dtype: float16 | |
``` | |