|
--- |
|
base_model: |
|
- NousResearch/Meta-Llama-3-8B-Instruct |
|
- Muhammad2003/Llama3-8B-OpenHermes-DPO |
|
- Kukedlc/LLama-3-8b-Maths |
|
- IlyaGusev/saiga_llama3_8b |
|
- ruslanmv/Medical-Llama3-8B |
|
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 [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [Muhammad2003/Llama3-8B-OpenHermes-DPO](https://huggingface.co/Muhammad2003/Llama3-8B-OpenHermes-DPO) |
|
* [Kukedlc/LLama-3-8b-Maths](https://huggingface.co/Kukedlc/LLama-3-8b-Maths) |
|
* [IlyaGusev/saiga_llama3_8b](https://huggingface.co/IlyaGusev/saiga_llama3_8b) |
|
* [ruslanmv/Medical-Llama3-8B](https://huggingface.co/ruslanmv/Medical-Llama3-8B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: NousResearch/Meta-Llama-3-8B-Instruct |
|
# no parameters necessary for base model |
|
- model: IlyaGusev/saiga_llama3_8b |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 |
|
- model: Muhammad2003/Llama3-8B-OpenHermes-DPO |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 |
|
- model: ruslanmv/Medical-Llama3-8B |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 |
|
- model: Kukedlc/LLama-3-8b-Maths |
|
parameters: |
|
density: 0.5 |
|
weight: 0.5 |
|
merge_method: ties |
|
base_model: NousResearch/Meta-Llama-3-8B-Instruct |
|
parameters: |
|
normalize: true |
|
dtype: bfloat16 |
|
|
|
``` |
|
|
