---
base_model:
- NousResearch/Meta-Llama-3.1-8B

- nvidia/Llama-3.1-Nemotron-Nano-8B-v1
- NousResearch/DeepHermes-3-Llama-3-8B-Preview
- deepcogito/cogito-v1-preview-llama-8B
- NousResearch/Meta-Llama-3.1-8B
- allenai/Llama-3.1-Tulu-3-8B-SFT
- NousResearch/Meta-Llama-3.1-8B-Instruct
- arcee-ai/Llama-3.1-SuperNova-Lite

- NousResearch/Hermes-3-Llama-3.1-8B
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
- Sao10K/L3-8B-Lunaris-v1
- TheDrummer/Llama-3SOME-8B-v2
- Gryphe/Pantheon-RP-1.0-8b-Llama-3
library_name: transformers
tags:
- mergekit
- merge

---
# output

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was first merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [NousResearch/Meta-Llama-3.1-8B](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B) as a base.

This model was merged using the NuSLERP merge method using [NousResearch/Meta-Llama-3.1-8B](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B) as a base.

### Models Merged

The following models were merged to helpful using the Model Stock merge method using [NousResearch/Meta-Llama-3.1-8B](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B) as a base:

- nvidia/Llama-3.1-Nemotron-Nano-8B-v1
- NousResearch/DeepHermes-3-Llama-3-8B-Preview
- deepcogito/cogito-v1-preview-llama-8B
- NousResearch/Meta-Llama-3.1-8B
- allenai/Llama-3.1-Tulu-3-8B-SFT
- NousResearch/Meta-Llama-3.1-8B-Instruct
- arcee-ai/Llama-3.1-SuperNova-Lite

The following models were merged to immersive using the Model Stock merge method using [NousResearch/Meta-Llama-3.1-8B](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B) as a base:

- NousResearch/Hermes-3-Llama-3.1-8B
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
- Sao10K/L3-8B-Lunaris-v1
- TheDrummer/Llama-3SOME-8B-v2
- Gryphe/Pantheon-RP-1.0-8b-Llama-3

Finally, the two models were merged using the [NuSLERP](https://arxiv.org/abs/2403.19522) merge method.

### Configuration

The following YAML configuration was used to produce this model:
[./config-helpful.yaml](./config-helpful.yaml)
[./config-immersive.yaml](./config-immersive.yaml)
[./config-basemerge.yaml](./config-basemerge.yaml)