---
base_model:
- arcee-ai/Llama-3.1-SuperNova-Lite
- Azazelle/Nimue-8B
- Replete-AI/L3-Pneuma-8B
- DreadPoor/Everything-COT-8B-r128-LoRA
- Nekochu/Luminia-8B-RP
- ResplendentAI/Theory_of_Mind_Llama3
- NousResearch/Hermes-3-Llama-3.1-8B
- kloodia/lora-8b-math
- refuelai/Llama-3-Refueled
- DreadPoor/OpenBioLLM-8B-r64-LoRA
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite) + [Azazelle/Nimue-8B](https://huggingface.co/Azazelle/Nimue-8B) as a base.

### Models Merged

The following models were included in the merge:
* [Replete-AI/L3-Pneuma-8B](https://huggingface.co/Replete-AI/L3-Pneuma-8B) + [DreadPoor/Everything-COT-8B-r128-LoRA](https://huggingface.co/DreadPoor/Everything-COT-8B-r128-LoRA)
* [Nekochu/Luminia-8B-RP](https://huggingface.co/Nekochu/Luminia-8B-RP) + [ResplendentAI/Theory_of_Mind_Llama3](https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3)
* [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) + [kloodia/lora-8b-math](https://huggingface.co/kloodia/lora-8b-math)
* [refuelai/Llama-3-Refueled](https://huggingface.co/refuelai/Llama-3-Refueled) + [DreadPoor/OpenBioLLM-8B-r64-LoRA](https://huggingface.co/DreadPoor/OpenBioLLM-8B-r64-LoRA)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: refuelai/Llama-3-Refueled+DreadPoor/OpenBioLLM-8B-r64-LoRA
  - model: Replete-AI/L3-Pneuma-8B+DreadPoor/Everything-COT-8B-r128-LoRA
  - model: Nekochu/Luminia-8B-RP+ResplendentAI/Theory_of_Mind_Llama3
  - model: NousResearch/Hermes-3-Llama-3.1-8B+kloodia/lora-8b-math
merge_method: model_stock
base_model: arcee-ai/Llama-3.1-SuperNova-Lite+Azazelle/Nimue-8B
normalize: false
int8_mask: true
dtype: bfloat16
```