---
base_model:
- allenai/Llama-3.1-Tulu-3-70B
- huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
- Sao10K/Llama-3.3-70B-Vulpecula-r1
- nbeerbower/llama3.1-kartoffeldes-70B
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 [huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [allenai/Llama-3.1-Tulu-3-70B](https://huggingface.co/allenai/Llama-3.1-Tulu-3-70B)
* [Sao10K/Llama-3.3-70B-Vulpecula-r1](https://huggingface.co/Sao10K/Llama-3.3-70B-Vulpecula-r1)
* [nbeerbower/llama3.1-kartoffeldes-70B](https://huggingface.co/nbeerbower/llama3.1-kartoffeldes-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
  - model: nbeerbower/llama3.1-kartoffeldes-70B
  - model: allenai/Llama-3.1-Tulu-3-70B
  - model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
base_model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
merge_method: model_stock
dtype: bfloat16
tokenizer:
  source: Sao10K/Llama-3.3-70B-Vulpecula-r1
```