---
base_model:
- Qwen/Qwen2.5-14B
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
library_name: transformers
tags:
- forgelm
- forge

---
# 681745b4-4ae0-4c5f-8e00-3bf6cdde855f

This is a forge of pre-trained language models created using [forgelm](https://github.com/AxeronAI/forgelm).

## Forge Details
### Forge Method

This model was forged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) forge method using [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) as a base.

### Models Forged

The following models were included in the forge:
* [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: Qwen/Qwen2.5-14B
dtype: bfloat16
forge_method: task_arithmetic
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 48]
        model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
        parameters:
          weight: 0.5
      - layer_range: [0, 48]
        model: Qwen/Qwen2.5-14B
```