---
base_model: unsloth/Qwen3-8B-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- qwen-3
- fine-tuning
- openmathreasoning
- python
- unsloth
- lora
- peft
- tutorial
- reasoning
- chat
license: apache-2.0
language:
- en
---

# krishanwalia30/Qwen3-16bit-OpenMathReasoning-Finetuned-Merged

🚀 **Harness the Power of Qwen-3 with Enhanced Reasoning and Chat!** 🚀

This model is a carefully fine-tuned version of the incredible [Qwen-3-8B](https://huggingface.co/Qwen/Qwen3-8B) using cutting-edge techniques with [Unsloth](https://github.com/unslothai/unsloth) and Parameter-Efficient Fine-Tuning (PEFT) via LoRA. It's designed to bring you the best of both worlds: the strong general capabilities of Qwen-3 with a significant boost in logical reasoning and engaging conversational skills.

We've taken the already powerful Qwen-3 and further sculpted it using a blend of the [unsloth/OpenMathReasoning-mini](https://huggingface.co/datasets/unsloth/OpenMathReasoning-mini) (Chain-of-Thought split) for advanced problem-solving and the [mlabonne/FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k) dataset to ensure natural and fluent interactions.

**🔥 Key Features:**

* **Enhanced Reasoning:** Excels at tasks requiring logical deduction and step-by-step thinking, thanks to fine-tuning on a dedicated reasoning dataset.
* **Improved Chat:** Maintains and enhances the general conversational abilities of Qwen-3, making it great for interactive applications.
* **Efficient Fine-Tuning:** Built using the incredibly efficient [Unsloth](https://github.com/unslothai/unsloth) library, resulting in faster training with less memory usage.
* **PEFT (LoRA) Inside:** Leverages Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning, making it easier to adapt to specific tasks without full model retraining.
* **Ready to Use:** Seamlessly integrates with the `transformers` library.


**🛠️ How to Get Started:**

Install the necessary libraries:

```bash
pip install transformers accelerate torch
```

Load and use the model:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "krishanwalia30/Qwen3-16bit-OpenMathReasoning-Finetuned-Merged"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="torch.float16")

messages = [
    {"role": "user", "content": "Explain the Pythagorean theorem in simple terms."},
    {"role": "assistant", "content": "Okay, here's a simple explanation:"},
    {"role": "user", "content": "Now, solve for the hypotenuse if a=3 and b=4."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7, top_p=0.8, top_k=20, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

**⚙️ Fine-tuning Details:**

* **Base Model:** [Qwen-3-8B](https://huggingface.co/Qwen/Qwen3-8B)
* **Fine-tuning Framework:** [Unsloth](https://github.com/unslothai/unsloth)
* **PEFT Strategy:** LoRA
* **Training Datasets:**
    * [unsloth/OpenMathReasoning-mini](https://huggingface.co/datasets/unsloth/OpenMathReasoning-mini) (COT split)
    * [mlabonne/FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k)
* **Training Ratio:** Approximately 30% reasoning data and 70% general chat data to balance capabilities.
* **Training Infrastructure:** Google Colab with a T4 GPU.
* **Quantization during Training:** Likely 4-bit quantization was employed during the fine-tuning process using Unsloth for memory efficiency. The final merged model is saved in 16-bit for broader compatibility.
* **Key Hyperparameters:**
    * `per_device_train_batch_size`: 2
    * `gradient_accumulation_steps`: 4
    * `learning_rate`: 2e-4
    * `max_steps`: 30
    * Optimizer: `adamw_8bit`
    * Learning Rate Scheduler: `linear`
    * Warmup Steps: 5
    * Weight Decay: 0.01
    * Seed: 3407

**📊 Evaluation:**

While rigorous quantitative evaluations are ongoing, initial assessments indicate a significant improvement in the model's ability to handle reasoning-based questions while maintaining strong general conversational skills. Further benchmarks and community feedback are welcome!

**👨‍💻 Author:**

[https://huggingface.co/krishanwalia30]

**🔗 Learn More:**

For a deeper dive into the fine-tuning process and the rationale behind the choices, check out the article: [https://medium.com/@krishanw30/b1a8f684c3f1].

**🙏 Acknowledgements:**

A big thank you to the brilliant teams at [Qwen](https://huggingface.co/Qwen), [Unsloth AI](https://github.com/unslothai/unsloth), and the creators of the [OpenMathReasoning-mini](https://huggingface.co/datasets/unsloth/OpenMathReasoning-mini) and [FineTome-100k](https://huggingface.co/datasets/mlabonne/FineTome-100k) datasets for making this project possible!


# Uploaded  model

- **Developed by:** krishanwalia30
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-8B-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)