---
base_model:
- failspy/Llama-3-8B-Instruct-MopeyMule
- kloodia/lora-8b-math
- failspy/Llama-3-8B-Instruct-MopeyMule
- Blackroot/Llama3-RP-Lora
- failspy/Llama-3-8B-Instruct-MopeyMule
- zementalist/llama-3-8B-chat-psychotherapist
- failspy/Llama-3-8B-Instruct-MopeyMule
- Blackroot/Llama-3-8B-Abomination-LORA
- failspy/Llama-3-8B-Instruct-MopeyMule
- ResplendentAI/Llama3_RP_ORPO_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 [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) + [Blackroot/Llama-3-8B-Abomination-LORA](https://huggingface.co/Blackroot/Llama-3-8B-Abomination-LORA) as a base.

### Models Merged

The following models were included in the merge:
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) + [kloodia/lora-8b-math](https://huggingface.co/kloodia/lora-8b-math)
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) + [Blackroot/Llama3-RP-Lora](https://huggingface.co/Blackroot/Llama3-RP-Lora)
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) + [zementalist/llama-3-8B-chat-psychotherapist](https://huggingface.co/zementalist/llama-3-8B-chat-psychotherapist)
* [failspy/Llama-3-8B-Instruct-MopeyMule](https://huggingface.co/failspy/Llama-3-8B-Instruct-MopeyMule) + [ResplendentAI/Llama3_RP_ORPO_LoRA](https://huggingface.co/ResplendentAI/Llama3_RP_ORPO_LoRA)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
 - model: failspy/Llama-3-8B-Instruct-MopeyMule+Blackroot/Llama3-RP-Lora
 - model: failspy/Llama-3-8B-Instruct-MopeyMule+zementalist/llama-3-8B-chat-psychotherapist
 - model: failspy/Llama-3-8B-Instruct-MopeyMule+ResplendentAI/Llama3_RP_ORPO_LoRA
 - model: failspy/Llama-3-8B-Instruct-MopeyMule+kloodia/lora-8b-math
merge_method: model_stock
base_model: failspy/Llama-3-8B-Instruct-MopeyMule+Blackroot/Llama-3-8B-Abomination-LORA
normalize: false
int8_mask: true
dtype: bfloat16
```