---
base_model:
- Novaciano/Judas-The-Uncensored-3.2-1B
- Novaciano/La_Mejor_Mezcla-3.2-1B
- Novaciano/BLAST_PROCESSING-3.2-1B
- diabolic6045/open-llama-3.2-1B-Instruct
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [diabolic6045/open-llama-3.2-1B-Instruct](https://huggingface.co/diabolic6045/open-llama-3.2-1B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [Novaciano/Judas-The-Uncensored-3.2-1B](https://huggingface.co/Novaciano/Judas-The-Uncensored-3.2-1B)
* [Novaciano/La_Mejor_Mezcla-3.2-1B](https://huggingface.co/Novaciano/La_Mejor_Mezcla-3.2-1B)
* [Novaciano/BLAST_PROCESSING-3.2-1B](https://huggingface.co/Novaciano/BLAST_PROCESSING-3.2-1B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
- model: Novaciano/La_Mejor_Mezcla-3.2-1B
- model: Novaciano/Judas-The-Uncensored-3.2-1B
- model: Novaciano/BLAST_PROCESSING-3.2-1B
base_model: diabolic6045/open-llama-3.2-1B-Instruct
merge_method: model_stock
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]
```