SOVL-Instruct-8B-L3 / README.md
saishf's picture
Update README.md
90046bb verified
---
license: cc-by-nc-4.0
base_model:
- meta-llama/Meta-Llama-3-8B-Instruct
- ResplendentAI/Smarts_Llama3
- meta-llama/Meta-Llama-3-8B-Instruct
- ResplendentAI/Aura_Llama3
- meta-llama/Meta-Llama-3-8B-Instruct
- ResplendentAI/BlueMoon_Llama3
- meta-llama/Meta-Llama-3-8B-Instruct
- ResplendentAI/RP_Format_QuoteAsterisk_Llama3
- meta-llama/Meta-Llama-3-8B-Instruct
- meta-llama/Meta-Llama-3-8B-Instruct
- ResplendentAI/Luna_Llama3
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
Request from [@Virt-io](https://huggingface.co./Virt-io)
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) as a base.
### Models Merged
The following models were included in the merge:
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) + [ResplendentAI/Smarts_Llama3](https://huggingface.co./ResplendentAI/Smarts_Llama3)
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) + [ResplendentAI/Aura_Llama3](https://huggingface.co./ResplendentAI/Aura_Llama3)
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co./ResplendentAI/BlueMoon_Llama3)
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) + [ResplendentAI/RP_Format_QuoteAsterisk_Llama3](https://huggingface.co./ResplendentAI/RP_Format_QuoteAsterisk_Llama3)
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-8B-Instruct) + [ResplendentAI/Luna_Llama3](https://huggingface.co./ResplendentAI/Luna_Llama3)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct+ResplendentAI/Aura_Llama3
- model: meta-llama/Meta-Llama-3-8B-Instruct+ResplendentAI/Smarts_Llama3
- model: meta-llama/Meta-Llama-3-8B-Instruct+ResplendentAI/Luna_Llama3
- model: meta-llama/Meta-Llama-3-8B-Instruct+ResplendentAI/BlueMoon_Llama3
- model: meta-llama/Meta-Llama-3-8B-Instruct+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
merge_method: model_stock
base_model: meta-llama/Meta-Llama-3-8B-Instruct
dtype: bfloat16
```