---
license: mit
language:
- en
base_model:
- Qwen/Qwen3-14B
---

> [!NOTE]
> **Use "You are an assistant with reasoning capabilities." system message to trigger gemini-style thinking.**


# Training Dataset

- The fine-tuning dataset consists of ~300 diverse examples, 160 of which are directly from Gemini 2.5 Pro.

# Model
- Trained on unsloth version of Qwen3-14B (instruct).
- No benchmark data for now.

  
**Keep in mind that it's slightly overfit since the training dataset was quite small. The model can be used to create more high quality examples for further training.**


![image/png](https://cdn-uploads.huggingface.co/production/uploads/6324eabf05bd8a54c6eb1650/TEBe1XQvpJA2IZ63btFWT.png)