Instructions to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Rauhan/Qwen2.5-3B-GRPO-GSM325")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Rauhan/Qwen2.5-3B-GRPO-GSM325")
model = AutoModelForMultimodalLM.from_pretrained("Rauhan/Qwen2.5-3B-GRPO-GSM325")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rauhan/Qwen2.5-3B-GRPO-GSM325"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rauhan/Qwen2.5-3B-GRPO-GSM325",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rauhan/Qwen2.5-3B-GRPO-GSM325

SGLang

How to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Rauhan/Qwen2.5-3B-GRPO-GSM325" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rauhan/Qwen2.5-3B-GRPO-GSM325",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Rauhan/Qwen2.5-3B-GRPO-GSM325" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rauhan/Qwen2.5-3B-GRPO-GSM325",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Rauhan/Qwen2.5-3B-GRPO-GSM325 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Rauhan/Qwen2.5-3B-GRPO-GSM325 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Rauhan/Qwen2.5-3B-GRPO-GSM325 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Rauhan/Qwen2.5-3B-GRPO-GSM325",
    max_seq_length=2048,
)

Docker Model Runner
How to use Rauhan/Qwen2.5-3B-GRPO-GSM325 with Docker Model Runner:
```
docker model run hf.co/Rauhan/Qwen2.5-3B-GRPO-GSM325
```

Qwen2.5-3B-GRPO-325

🚀 Qwen2.5-3B-GRPO-325 is a fine-tuned version of Qwen2.5 3B, trained using GRPO (Guided Reinforcement Policy Optimization) and DeepSeek R1’s open-source recipe. This model significantly enhances the base Qwen2.5-3B in mathematical problem-solving, logical reasoning, and structured response generation, pushing it towards GPT-4o1-style advanced reasoning.

🔥 Trained entirely on a Free Google Colab Tesla T4 GPU: Training Notebook

🚀 Try inference using this Google Colab notebook: Inference Notebook

🚀 With more resources and extended training, this model could be pushed even further!

Model Details

Base Model: unsloth/Qwen2.5-3B-instruct-unsloth-bnb-4bit
Fine-tuning Method: GRPO with structured reinforcement
Dataset: 325 curated questions from GSM8K (math reasoning)
Format Adherence: XML-based structured reasoning
Notable Improvements:
- Mathematical accuracy ✔
- Logical consistency ✔
- Structured XML-format responses ✔
- GPT-4o1-like step-by-step reasoning ✔

Usage

Example Input & Output

Input (User Query)

If 2x+5=10. Solve for x.

Output (Model Response)

<reasoning>
To solve for x, we need to isolate x on one side of the equation. This can be done by subtracting 5 from both sides of the equation.
</reasoning>
<answer>
2x + 5 - 5 = 10 - 5,
2x = 5,
2x / 2 = 5 / 2,
x = 2.5
</answer>

Installation & Inference

Hugging Face Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Rauhan/Qwen2.5-3B-GRPO-325"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Limitations & Future Work

🚧 Limitations:

Limited by small dataset size (325 questions)
Training done on a single Free Google Colab Tesla T4 GPU
Some long-form reasoning may need further fine-tuning

🚀 Future Improvements:

Training on a larger dataset (more GSM8K questions + other logical reasoning datasets)
Extending fine-tuning using DeepSeek R1’s full training pipeline
Further quantization for faster and memory-efficient inference

License & Citation

This model is released under Apache 2.0 License. If you use this model in your research, please cite:

@misc{Qwen2.5-3B-GRPO-325,
  author = {Rauhan},
  title = {Qwen2.5-3B-GRPO-325},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/Rauhan/Qwen2.5-3B-GRPO-325}
}

🚀 This model demonstrates how even small models can achieve great results with the right fine-tuning techniques! 🚀

About the Author

🔗 Portfolio & Contact Information:

🌍 Website: rauhanahmed.org
🏢 GitHub: github.com/rauhanAhmed
💼 LinkedIn: linkedin.com/in/rauhan-ahmed
🐦 Twitter (X): x.com/ahmed_rauh46040
📧 Email: rauhaan.siddiqui@gmail.com

Feel free to reach out for collaborations, AI research, or any inquiries! 🚀

Downloads last month: 2

Safetensors

Model size

3B params

Tensor type

F16

Rauhan
/

Qwen2.5-3B-GRPO-GSM325