---
base_model: Qwen/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: Qwen2.5-1.5B-Thinking
tags:
- generated_from_trainer
- trl
- grpo
licence: license
datasets:
- microsoft/orca-math-word-problems-200k
---

# Model Card for Qwen2.5-1.5B-Thinking

This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).

## Quick start

```python
from transformers import pipeline

question = "Mia can decorate 2 dozen Easter eggs per hour. Her little brother Billy can only decorate 10 eggs per hour. They need to decorate 170 eggs for the Easter egg hunt. If they work together, how long will it take them to decorate all the eggs?"
generator = pipeline("text-generation", model="justinj92/Qwen2.5-1.5B-Thinking", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/justinjoy-5/huggingface/runs/bkaa9r09) 

<img src="https://huggingface.co/justinj92/Qwen-1.5B-GRPO/resolve/main/w%26b_qwen_r1.png" width="1024" height="800"/>

Trained on 1xH100 96GB via Azure Cloud

This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

### Framework versions

- TRL: 0.15.0.dev0
- Transformers: 4.49.0.dev0
- Pytorch: 2.5.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## Citations

Cite GRPO as:

```bibtex
@article{zhihong2024deepseekmath,
    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
    year         = 2024,
    eprint       = {arXiv:2402.03300},
}

```

Cite TRL as:
    
```bibtex
@misc{vonwerra2022trl,
	title        = {{TRL: Transformer Reinforcement Learning}},
	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```