---
base_model:
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/Luna_Llama3
- MrRobotoAI/Hathor-v4.7
- Azazelle/Llama-3-LongStory-LORA
- MrRobotoAI/Hathor-v4.7
- Azazelle/Llama-3-8B-Abomination-LORA
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/NoWarning_Llama3
- MrRobotoAI/Hathor-v4.7
- Azazelle/L3-Daybreak-8b-lora
- MrRobotoAI/Hathor-v4.7
- vincentyandex/lora_llama3_chunked_novel_bs128
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/BlueMoon_Llama3
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/Llama3_RP_ORPO_LoRA
- MrRobotoAI/Hathor-v4.7
- MrRobotoAI/Hathor-v4.7
- Blackroot/Llama-3-LongStory-LORA
- MrRobotoAI/Hathor-v4.7
- Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
- MrRobotoAI/Hathor-v4.7
- Azazelle/Smarts_Llama3
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/Theory_of_Mind_Llama3
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/Aura_Llama3
- MrRobotoAI/Hathor-v4.7
- nicce/story-mixtral-8x7b-lora
- MrRobotoAI/Hathor-v4.7
- Azazelle/Nimue-8B
- MrRobotoAI/Hathor-v4.7
- ResplendentAI/Llama3_Aesir_Preview_LoRA_128
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 [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) as a base.

### Models Merged

The following models were included in the merge:
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/Llama-3-LongStory-LORA](https://huggingface.co/Azazelle/Llama-3-LongStory-LORA)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/Llama-3-8B-Abomination-LORA](https://huggingface.co/Azazelle/Llama-3-8B-Abomination-LORA)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/NoWarning_Llama3](https://huggingface.co/ResplendentAI/NoWarning_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/L3-Daybreak-8b-lora](https://huggingface.co/Azazelle/L3-Daybreak-8b-lora)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [vincentyandex/lora_llama3_chunked_novel_bs128](https://huggingface.co/vincentyandex/lora_llama3_chunked_novel_bs128)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/Llama3_RP_ORPO_LoRA](https://huggingface.co/ResplendentAI/Llama3_RP_ORPO_LoRA)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Blackroot/Llama-3-LongStory-LORA](https://huggingface.co/Blackroot/Llama-3-LongStory-LORA)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B](https://huggingface.co/Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/Smarts_Llama3](https://huggingface.co/Azazelle/Smarts_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/Theory_of_Mind_Llama3](https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [nicce/story-mixtral-8x7b-lora](https://huggingface.co/nicce/story-mixtral-8x7b-lora)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [Azazelle/Nimue-8B](https://huggingface.co/Azazelle/Nimue-8B)
* [MrRobotoAI/Hathor-v4.7](https://huggingface.co/MrRobotoAI/Hathor-v4.7) + [ResplendentAI/Llama3_Aesir_Preview_LoRA_128](https://huggingface.co/ResplendentAI/Llama3_Aesir_Preview_LoRA_128)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:

  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/Aura_Llama3
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/Luna_Llama3
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/BlueMoon_Llama3
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/Llama3_Aesir_Preview_LoRA_128
  - model: MrRobotoAI/Hathor-v4.7+ResplendentAI/Llama3_RP_ORPO_LoRA
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/Llama-3-8B-Abomination-LORA
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/Nimue-8B
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/Smarts_Llama3
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/L3-Daybreak-8b-lora
  - model: MrRobotoAI/Hathor-v4.7+Azazelle/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Hathor-v4.7+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/Hathor-v4.7+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Hathor-v4.7+nicce/story-mixtral-8x7b-lora

merge_method: model_stock
base_model: MrRobotoAI/Hathor-v4.7
parameters:
  normalize: true
  int8_mask: true
dtype: float16
```