README.md

---
base_model:
- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
- Qwen/Qwen3-8B
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 [Linear](https://arxiv.org/abs/2203.05482) merge method using [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B) as a base.

### Models Merged

The following models were included in the merge:
* [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
    parameters:
      weight: 1
  - model: Qwen/Qwen3-8B
    parameters:
      weight: 0
merge_method: linear
base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
parameters:
  normalize: false
tokenizer:
  source: "Qwen/Qwen3-8B"
  tokens: 
    <|endoftext|>:
      source: "Qwen/Qwen3-8B"
    <|im_end|>:
      source: "Qwen/Qwen3-8B"
    <｜end▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜end▁of▁sentence｜>"
      force: true
    <｜User｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜User｜>"
      force: true
    <｜Assistant｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜Assistant｜>"
      force: true
    <｜begin▁of▁sentence｜>:
      source: 
        model: "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
        kind: "model_token"
        token: "<｜begin▁of▁sentence｜>"
      force: true
dtype: bfloat16


```