---
base_model:
- refuelai/Llama-3-Refueled
- DreadPoor/OpenBioLLM-8B-r64-LoRA
- FuseAI/FuseChat-Llama-3.1-8B-Instruct
- DreadPoor/MathLingo-8B-r128-LORA
- Replete-AI/L3-Pneuma-8B
- DreadPoor/Everything-COT-8B-r128-LoRA
- Nekochu/Luminia-8B-RP
- bunnycore/Llama-3.1-8b-smart-lora
- T145/ZEUS-8B-V2
- Azazelle/Nimue-8B
- unsloth/Meta-Llama-3.1-8B-Instruct
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 [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [refuelai/Llama-3-Refueled](https://huggingface.co/refuelai/Llama-3-Refueled) + [DreadPoor/OpenBioLLM-8B-r64-LoRA](https://huggingface.co/DreadPoor/OpenBioLLM-8B-r64-LoRA)
* [FuseAI/FuseChat-Llama-3.1-8B-Instruct](https://huggingface.co/FuseAI/FuseChat-Llama-3.1-8B-Instruct) + [DreadPoor/MathLingo-8B-r128-LORA](https://huggingface.co/DreadPoor/MathLingo-8B-r128-LORA)
* [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) + [bunnycore/Llama-3.1-8b-smart-lora](https://huggingface.co/bunnycore/Llama-3.1-8b-smart-lora)
* [T145/ZEUS-8B-V2](https://huggingface.co/T145/ZEUS-8B-V2) + [Azazelle/Nimue-8B](https://huggingface.co/Azazelle/Nimue-8B)

### 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+bunnycore/Llama-3.1-8b-smart-lora 
  - model: FuseAI/FuseChat-Llama-3.1-8B-Instruct+DreadPoor/MathLingo-8B-r128-LORA
  - model: T145/ZEUS-8B-V2+Azazelle/Nimue-8B
merge_method: model_stock
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
normalize: false
filter_wise: true
chat_template: "auto"
int8_mask: true
dtype: bfloat16

```