---
base_model:
- meta-llama/Llama-3.2-3B
- Alelcv27/Llama3.2-3B-Base-Math
- Alelcv27/Llama3.2-3B-Base-Code
library_name: transformers
tags:
- mergekit
- merge

---
# Llama3.2-3B-DELLA-Math-Code

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 [DELLA](https://arxiv.org/abs/2406.11617) merge method using [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) as a base.

### Models Merged

The following models were included in the merge:
* [Alelcv27/Llama3.2-3B-Base-Math](https://huggingface.co/Alelcv27/Llama3.2-3B-Base-Math)
* [Alelcv27/Llama3.2-3B-Base-Code](https://huggingface.co/Alelcv27/Llama3.2-3B-Base-Code)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: meta-llama/Llama-3.2-3B
dtype: float16
merge_method: della
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: Alelcv27/Llama3.2-3B-Base-Code
        parameters:
          density: 0.8
          weight: 0.7
      - layer_range: [0, 28]
        model: Alelcv27/Llama3.2-3B-Base-Math
        parameters:
          density: 0.7
          weight: 0.5
      - layer_range: [0, 28]
        model: meta-llama/Llama-3.2-3B
parameters:
  epsilon: 0.1
  lambda: 0.9
  normalize: 1.0
```