---
base_model:
- baslak/Llama-3.2-3B-Instruct-CodeRev
- unsloth/Llama-3.2-3B
- KingNish/Reasoning-Llama-3b-v0.1
- Hastagaras/L3.2-JametMini-3B-MK.I
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 [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) as a base.

### Models Merged

The following models were included in the merge:
* [baslak/Llama-3.2-3B-Instruct-CodeRev](https://huggingface.co/baslak/Llama-3.2-3B-Instruct-CodeRev)
* [KingNish/Reasoning-Llama-3b-v0.1](https://huggingface.co/KingNish/Reasoning-Llama-3b-v0.1)
* [Hastagaras/L3.2-JametMini-3B-MK.I](https://huggingface.co/Hastagaras/L3.2-JametMini-3B-MK.I)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Hastagaras/L3.2-JametMini-3B-MK.I
    parameters:
      density: 0.5
      weight: 0.5
  - model: KingNish/Reasoning-Llama-3b-v0.1
    parameters:
      density: 0.4
      weight: 0.4
  - model: baslak/Llama-3.2-3B-Instruct-CodeRev
    parameters:
      density: 0.2
      weight: 0.2
  - model: Hastagaras/L3.2-JametMini-3B-MK.I
    parameters:
      density: 0.3
      weight: 0.3


merge_method: ties
base_model: unsloth/Llama-3.2-3B
parameters:
  density: 1
  normalize: false
  int8_mask: true
dtype: float16

```