---
base_model:
- CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary
- bunnycore/Llama-3.2-1B-Instruct-RP
- marcuscedricridia/badllama3.2-1B
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 [bunnycore/Llama-3.2-1B-Instruct-RP](https://huggingface.co/bunnycore/Llama-3.2-1B-Instruct-RP) as a base.

### Models Merged

The following models were included in the merge:
* [CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary](https://huggingface.co/CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary)
* [marcuscedricridia/badllama3.2-1B](https://huggingface.co/marcuscedricridia/badllama3.2-1B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
- model: marcuscedricridia/badllama3.2-1B
- model: CodeAtCMU/Llama-3.2-1B-GenerativePerturbations_full_sft_code_data_120K_imaginary

merge_method: model_stock
base_model: bunnycore/Llama-3.2-1B-Instruct-RP
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0]
```