---
base_model:
- Heralax/Augmental-13b-v1.50_B
- ChaiML/season_4_top_solution
- NeverSleep/Noromaid-13b-v0.3
- TheBloke/Llama-2-13B-fp16
- Fredithefish/RP_Base
tags:
- mergekit
- merge

---
# waterbuck

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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) as a base.

### Models Merged

The following models were included in the merge:
* [Heralax/Augmental-13b-v1.50_B](https://huggingface.co/Heralax/Augmental-13b-v1.50_B)
* [ChaiML/season_4_top_solution](https://huggingface.co/ChaiML/season_4_top_solution)
* [NeverSleep/Noromaid-13b-v0.3](https://huggingface.co/NeverSleep/Noromaid-13b-v0.3)
* [Fredithefish/RP_Base](https://huggingface.co/Fredithefish/RP_Base)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
- model: Heralax/Augmental-13b-v1.50_B
  parameters:
    density: 0.5
    weight: 0.3
- model: Fredithefish/RP_Base
  parameters:
    density: 0.5
    weight: 0.6
- model: NeverSleep/Noromaid-13b-v0.3
  parameters:
    density: 0.5
    weight: 0.5
- model: ChaiML/season_4_top_solution
  parameters:
    density: 0.5
    weight: 0.5

base_model: TheBloke/Llama-2-13B-fp16
merge_method: dare_ties
parameters:
  normalize: 1.0

```