---
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- Anannta/Qwen-STEM-Specialist-7B
library_name: transformers
tags:
- mergekit
- merge

---
# R1-STEM-Coder-7B

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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
* [Anannta/Qwen-STEM-Specialist-7B](https://huggingface.co/Anannta/Qwen-STEM-Specialist-7B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

merge_method: slerp
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
dtype: bfloat16
tokenizer_source: base
models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
  - model: Anannta/Qwen-STEM-Specialist-7B
parameters:
  t:
    - filter: "lm_head"
      value: 0.0
    - filter: "model.embed_tokens"
      value: 0.0
    - value: [0.0, 0.5, 0.5, 0.0]

```