---
base_model:
- TheBloke/Llama-2-13B-fp16
- Masterjp123/SnowyRP-FinalV1-L2-13B
- Masterjp123/Snowyrp-V2B-P1
- sauce1337/BerrySauce-L2-13b
library_name: transformers
tags:
- mergekit
- merge

---
# merged

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details

Made as a test model, not sure about quality, probably will not make any quants unless someone finds out it's good and asks.

### Merge Method

This model was merged using the [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:
* [Masterjp123/SnowyRP-FinalV1-L2-13B](https://huggingface.co/Masterjp123/SnowyRP-FinalV1-L2-13B)
* [posicube/Llama2-chat-AYB-13B](https://huggingface.co/posicube/Llama2-chat-AYB-13B)
* [Sao10K/Stheno-1.8-L2-13B](https://huggingface.co/Sao10K/Stheno-1.8-L2-13B)
* [ValiantLabs/ShiningValiantXS](https://huggingface.co/ValiantLabs/ShiningValiantXS)
* [sauce1337/BerrySauce-L2-13b](https://huggingface.co/sauce1337/BerrySauce-L2-13b)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model:
  model:
    path: TheBloke/Llama-2-13B-fp16
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 40]
    model:
      model:
        path: Masterjp123/Snowyrp-V2B-P1
    parameters:
      density: [1.0, 0.7, 0.1]
      weight: 1.0
  - layer_range: [0, 40]
    model:
      model:
        path: Masterjp123/SnowyRP-FinalV1-L2-13B
    parameters:
      density: 0.5
      weight: [0.0, 0.3, 0.7, 1.0]
  - layer_range: [0, 40]
    model:
      model:
        path: sauce1337/BerrySauce-L2-13b
    parameters:
      density: 0.33
      weight:
      - filter: mlp
        value: 0.5
      - value: 0.0
  - layer_range: [0, 40]
    model:
      model:
        path: TheBloke/Llama-2-13B-fp16
```
for Masterjp123/Snowyrp-V2B-P1
```yaml
base_model:
  model:
    path: TheBloke/Llama-2-13B-fp16
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 40]
    model:
      model:
        path: Sao10K/Stheno-1.8-L2-13B
    parameters:
      density: [1.0, 0.7, 0.1]
      weight: 1.0
  - layer_range: [0, 40]
    model:
      model:
        path: ValiantLabs/ShiningValiantXS
    parameters:
      density: 0.5
      weight: [0.0, 0.3, 0.7, 1.0]
  - layer_range: [0, 40]
    model:
      model:
        path: posicube/Llama2-chat-AYB-13B
    parameters:
      density: 0.33
      weight:
      - filter: mlp
        value: 0.5
      - value: 0.0
  - layer_range: [0, 40]
    model:
      model:
        path: TheBloke/Llama-2-13B-fp16
```