---
base_model:
- Qwen/Qwen3-4B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- reasoning
- think
- deepseek
license: apache-2.0
language:
- en
datasets:
- sequelbox/Celestia3-DeepSeek-R1-0528
- LuyiCui/Mixture-of-Thoughts-processed
---

# Uploaded finetuned  model

- **Developed by:** ertghiu256
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-4b-unsloth-bnb-4bit

This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

# Model information
This is Qwen 3 4b parameters finetuned on 18k samples from sequelbox/Celestia3-DeepSeek-R1-0528 dataset that is distilled from Deepseek R1 0528.

## Model purposes
- General reasoning
- Code (note: this model is not trained on html code, so the html code generated might look horible)
- Solving problems

### Note: This model development is not from the deepseek team.