---
datasets:
- Liontix/gemini-2.5-pro-200x
- Liontix/gemini-2.5-flash-100x
base_model:
- unsloth/Qwen3-8B-unsloth-bnb-4bit
---
This model was trained on a Gemini 2.5 Flash (non-reasoning) dataset and a Gemini 2.5 Pro (reasoning) dataset. It is a reasoning model.

You can request distilled models or datasets [here](https://huggingface.co/Liontix/Qwen3-8B-Gemini-2.5-Pro-Distill/discussions)

If you want to fine-tune this model, then you can start from [here](https://huggingface.co/Liontix/Qwen3-8B-Gemini-2.5-Pro-Distill/blob/main/Unsloth_Qwen3_Reasoning_Conversational_Edited.ipynb), a slightly modified unsloth Jupyter notebook.