---
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- avemio/German-RAG-x-HERMES-LLAMA-MERGED-EXP
- mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [avemio/German-RAG-x-HERMES-LLAMA-MERGED-EXP](https://huggingface.co/avemio/German-RAG-x-HERMES-LLAMA-MERGED-EXP) as a base.

### Models Merged

The following models were included in the merge:
* [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)
* [mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1](https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: avemio/German-RAG-x-HERMES-LLAMA-MERGED-EXP
    # no parameters necessary for base model
  - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1
    parameters:
      density: 0.5
      weight: 0.5
  - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: dare_ties
base_model: avemio/German-RAG-x-HERMES-LLAMA-MERGED-EXP
tokenizer_source: union
chat_template: chatml
normalize: false
int8_mask: true
dtype: float16

```