---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# merge2

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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using /kaggle/input/meta-llama-3-8b-instruct/transformers/hf/1 as a base.

### Models Merged

The following models were included in the merge:
* /kaggle/input/meta-llama-3-8b/transformers/hf/1

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  # Finetune model
  - model: /kaggle/input/meta-llama-3-8b-instruct/transformers/hf/1
    parameters:
      weight: 1.0
  # Base model
  - model: /kaggle/input/meta-llama-3-8b/transformers/hf/1
    parameters:
      weight: -1.0
merge_method: task_arithmetic
base_model: /kaggle/input/meta-llama-3-8b-instruct/transformers/hf/1
parameters:
  normalize: false
dtype: float32

```