---
base_model:
- MrRobotoAI/MrRoboto-BASE-v2.1-8b-64k
- Blackroot/Llama-3-LongStory-LORA
- gradientai/Llama-3-8B-Instruct-Gradient-4194k
- MrRobotoAI/MrRoboto-BASE-v1-8b-64k
- Blackroot/Llama-3-LongStory-LORA
- MrRobotoAI/Llama-3-8B-Uncensored-test8
- Blackroot/Llama-3-LongStory-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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [MrRobotoAI/MrRoboto-BASE-v2.1-8b-64k](https://huggingface.co/MrRobotoAI/MrRoboto-BASE-v2.1-8b-64k) + [Blackroot/Llama-3-LongStory-LORA](https://huggingface.co/Blackroot/Llama-3-LongStory-LORA) as a base.

### Models Merged

The following models were included in the merge:
* [gradientai/Llama-3-8B-Instruct-Gradient-4194k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-4194k)
* [MrRobotoAI/MrRoboto-BASE-v1-8b-64k](https://huggingface.co/MrRobotoAI/MrRoboto-BASE-v1-8b-64k) + [Blackroot/Llama-3-LongStory-LORA](https://huggingface.co/Blackroot/Llama-3-LongStory-LORA)
* [MrRobotoAI/Llama-3-8B-Uncensored-test8](https://huggingface.co/MrRobotoAI/Llama-3-8B-Uncensored-test8) + [Blackroot/Llama-3-LongStory-LORA](https://huggingface.co/Blackroot/Llama-3-LongStory-LORA)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: MrRobotoAI/MrRoboto-BASE-v1-8b-64k+Blackroot/Llama-3-LongStory-LORA
    parameters:
      density: 0.2
      weight: 0.4
  - model: MrRobotoAI/MrRoboto-BASE-v2.1-8b-64k+Blackroot/Llama-3-LongStory-LORA
    parameters:
      density: 0.5
      weight: 0.9
  - model: MrRobotoAI/Llama-3-8B-Uncensored-test8+Blackroot/Llama-3-LongStory-LORA
    parameters:
      density: 0.5
      weight: 0.9
  - model: gradientai/Llama-3-8B-Instruct-Gradient-4194k
    parameters:
      density: 0.2
      weight: 0.4
merge_method: ties
base_model: MrRobotoAI/MrRoboto-BASE-v2.1-8b-64k+Blackroot/Llama-3-LongStory-LORA
parameters:
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
```